{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:55:43Z","timestamp":1774554943289,"version":"3.50.1"},"reference-count":224,"publisher":"Emerald","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,4,25]]},"abstract":"<jats:p>Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new possibilities for data compression, allowing compression algorithms to be learned end-to-end from data using powerful generative models such as normalizing flows, variational autoencoders, diffusion probabilistic models, and generative adversarial networks. This monograph aims to introduce this field of research to a broader machine learning audience by reviewing the necessary background in information theory (e.g., entropy coding, rate-distortion theory) and computer vision (e.g., image quality assessment, perceptual metrics), and providing a curated guide through the essential ideas and methods in the literature thus far.<\/jats:p>","DOI":"10.1561\/0600000107","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T08:32:19Z","timestamp":1682411539000},"page":"113-200","source":"Crossref","is-referenced-by-count":54,"title":["An Introduction to Neural Data Compression"],"prefix":"10.1561","volume":"15","author":[{"given":"Yibo","family":"Yang","sequence":"first","affiliation":[{"name":"University of California , Irvine,","place":["USA"]}]},{"given":"Stephan","family":"Mandt","sequence":"additional","affiliation":[{"name":"University of California , Irvine,","place":["USA"]}]},{"given":"Lucas","family":"Theis","sequence":"additional","affiliation":[{"name":"Google Research ,","place":["USA"]}]}],"member":"140","published-online":{"date-parts":[[2023,4,25]]},"reference":[{"key":"2026032615164100800_ref001","first-page":"1141","article-title":"Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations","volume":"30","author":"Agustsson","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref002","article-title":"Universally Quantized Neural Compression","volume":"33","author":"Agustsson","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref003","first-page":"221","article-title":"Generative adversarial networks for extreme learned image compression","volume-title":"The IEEE International Conference on Computer Vision (ICCV)","author":"Agustsson","year":"2019"},{"key":"2026032615164100800_ref004","first-page":"8503","article-title":"Scale-space flow for end-to-end optimized video compression","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Agustsson","year":"2020"},{"key":"2026032615164100800_ref005","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/T-C.1974.223784","article-title":"Discrete cosine transform","volume":"C-23","author":"Ahmed","year":"1974","journal-title":"IEEE Transactions on Computers"},{"key":"2026032615164100800_ref006","first-page":"159","volume-title":"International Conference on Machine Learning","author":"Alemi","year":"2018"},{"key":"2026032615164100800_ref007","article-title":"Deep variational information bottleneck","volume-title":"arXiv preprint arXiv:1612.00410","author":"Alemi","year":"2016"},{"key":"2026032615164100800_ref008","first-page":"12 226","article-title":"Understanding and simplifying perceptual distances","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Amir","year":"2021"},{"issue":"1","key":"2026032615164100800_ref009","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/TIT.1972.1054753","article-title":"An algorithm for computing the capacity of arbitrary discrete memoryless channels","volume":"18","author":"Arimoto","year":"1972","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026032615164100800_ref010","article-title":"Nonlinear transform coding","volume":"15","author":"Ball\u00e9","year":"2021","journal-title":"IEEE Trans. on Special Topics in Signal Processing"},{"key":"2026032615164100800_ref011","doi-asserted-by":"crossref","DOI":"10.1109\/PCS.2016.7906310","article-title":"End-to-end optimization of nonlinear transform codes for perceptual quality","volume-title":"Picture Coding Symposium","author":"Ball\u00e9","year":"2016"},{"key":"2026032615164100800_ref012","article-title":"End-to-end Optimized Image Compression","volume-title":"International Conference on Learning Representations","author":"Ball\u00e9","year":"2017"},{"key":"2026032615164100800_ref013","article-title":"Integer networks for data compression with latent-variable models","volume-title":"International Conference on Learning Representations","author":"Ball\u00e9","year":"2018"},{"key":"2026032615164100800_ref014","article-title":"Variational Image Compression with a Scale Hyperprior","volume-title":"International Conference on Learning Representations","author":"Ball\u00e9","year":"2018"},{"key":"2026032615164100800_ref015","article-title":"Understanding Entropy Coding With Asymmetric Numeral Systems (ANS): a Statistician\u2019s Perspective","volume-title":"arXiv preprint arXiv:2201.01741","author":"Bamler","year":"2022"},{"key":"2026032615164100800_ref016","volume-title":"Lossless Data Compression with Neural Networks","author":"Bellard","year":"2019"},{"key":"2026032615164100800_ref017","volume-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"issue":"10","key":"2026032615164100800_ref018","doi-asserted-by":"crossref","DOI":"10.1109\/TIT.2002.802612","article-title":"Entanglement-Assisted Capacity of a Quantum Channel and the Reverse Shannon Theorem","volume":"48","author":"Bennett","year":"2002","journal-title":"IEEE Transactions on Information Theory"},{"issue":"6","key":"2026032615164100800_ref019","doi-asserted-by":"crossref","first-page":"2693","DOI":"10.1109\/18.720552","article-title":"Lossy source coding","volume":"44","author":"Berger","year":"1998","journal-title":"IEEE Transactions on Information Theory"},{"issue":"2-3","key":"2026032615164100800_ref020","doi-asserted-by":"crossref","first-page":"174","DOI":"10.5964\/bioling.8783","article-title":"Analysis by synthesis: A (re-) emerging program of research for language and vision","volume":"4","author":"Bever","year":"2010","journal-title":"Biolinguistics"},{"key":"2026032615164100800_ref021","first-page":"13","volume-title":"Advances in Neural Information Processing Systems","author":"Bhardwaj","year":"2020"},{"key":"2026032615164100800_ref022","first-page":"1","volume-title":"2021 Picture Coding Symposium (PCS)","author":"Bird","year":"2021"},{"key":"2026032615164100800_ref023","doi-asserted-by":"publisher","DOI":"10.1117\/1.2819119","volume-title":"Information science and statistics","author":"Bishop","year":"2006"},{"issue":"4","key":"2026032615164100800_ref024","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1109\/TIT.1972.1054855","article-title":"Computation of channel capacity and rate-distortion functions","volume":"18","author":"Blahut","year":"1972","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026032615164100800_ref025","doi-asserted-by":"crossref","first-page":"6228","DOI":"10.1109\/CVPR.2018.00652","article-title":"The perception-distortion tradeoff","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Blau","year":"2018"},{"key":"2026032615164100800_ref026","volume-title":"Introduction to Data Compression","author":"Blelloch","year":"2013"},{"key":"2026032615164100800_ref027","article-title":"Vorlesungen \u00fcber Gastheorie,(2 volumes)","volume-title":"Leipzig (1895, 1898)","author":"Boltzmann","year":"1895"},{"key":"2026032615164100800_ref028","doi-asserted-by":"publisher","first-page":"3773","DOI":"10.1109\/ICIP.2016.7533065","article-title":"A deep neural network for image quality assessment","volume-title":"2016 IEEE International Conference on Image Processing (ICIP)","author":"Bosse","year":"2016"},{"issue":"4","key":"2026032615164100800_ref029","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/BF00332918","article-title":"Auto-association by multilayer perceptrons and singular value decomposition","volume":"59","author":"Bourlard","year":"1988","journal-title":"Biological cybernetics"},{"key":"2026032615164100800_ref030","article-title":"Super-resolution with deep convolutional sufficient statistics","volume-title":"International Conference on Learning Representations","author":"Bruna","year":"2016"},{"issue":"8","key":"2026032615164100800_ref031","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1109\/TPAMI.2012.230","article-title":"Invariant scattering convolution networks","volume":"35","author":"Bruna","year":"2013","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026032615164100800_ref032","article-title":"Importance weighted autoencoders","volume-title":"arXiv preprint arXiv:1509.00519","author":"Burda","year":"2015"},{"key":"2026032615164100800_ref033","first-page":"1","volume-title":"2017 IEEE Visual Communications and Image Processing (VCIP)","author":"Chen","year":"2017"},{"key":"2026032615164100800_ref034","first-page":"864","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Chen","year":"2018"},{"key":"2026032615164100800_ref035","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.00796","article-title":"Learned image compression with discretized gaussian mixture likelihoods and attention modules","volume-title":"arXiv preprint arXiv:2001.01568","author":"Cheng","year":"2020"},{"key":"2026032615164100800_ref036","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00324","article-title":"Variable rate deep image compression with a conditional autoencoder","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Choi","year":"2019"},{"issue":"1","key":"2026032615164100800_ref037","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/29.17498","article-title":"Entropy-constrained vector quantization","volume":"37","author":"Chou","year":"1989","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"2026032615164100800_ref038","volume-title":"Mechanical Theory of Heat","author":"Clausius","year":"1850"},{"key":"2026032615164100800_ref039","volume-title":"Elements of Information Theory","author":"Cover","year":"2006"},{"key":"2026032615164100800_ref040","first-page":"1078","article-title":"Inference suboptimality in variational autoencoders","volume-title":"International Conference on Machine Learning","author":"Cremer","year":"2018"},{"key":"2026032615164100800_ref041","doi-asserted-by":"crossref","first-page":"1393","DOI":"10.1109\/ISIT.2008.4595216","article-title":"Communication requirements for generating correlated random variables","volume-title":"2008 IEEE International Symposium on Information Theory","author":"Cuff","year":"2008"},{"key":"2026032615164100800_ref042","doi-asserted-by":"crossref","DOI":"10.1109\/ITW.2013.6691298","article-title":"The likelihood encoder for source coding","volume-title":"2013 IEEE Information Theory Workshop","author":"Cuff","year":"2013"},{"key":"2026032615164100800_ref043","unstructured":"J.\n              Degrave\n             and I.Korshunova, How we can make machine learning algorithms tunable. URL: https:\/\/www.engraved.blog\/how-we-can-make-machine-learning-algorithms-tunable\/."},{"key":"2026032615164100800_ref044","first-page":"1486","article-title":"Deep generative image models using a Laplacian pyramid of adversarial networks","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Denton","year":"2015"},{"issue":"129","key":"2026032615164100800_ref045","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1007\/s11263-020-01419-7","article-title":"Comparison of Full-Reference Image Quality Models for Optimization of Image Processing Systems","author":"Ding","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"2026032615164100800_ref046","article-title":"Nice: Non-linear independent components estimation","volume-title":"arXiv preprint arXiv:1410.8516","author":"Dinh","year":"2014"},{"key":"2026032615164100800_ref047","article-title":"Density estimation using real nvp","volume-title":"arXiv preprint arXiv:1605.08803","author":"Dinh","year":"2016"},{"key":"2026032615164100800_ref048","first-page":"6421","article-title":"Neural inter-frame compression for video coding","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Djelouah","year":"2019"},{"issue":"2","key":"2026032615164100800_ref049","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","article-title":"Image super-resolution using deep convolutional networks","volume":"38","author":"Dong","year":"2015","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2026032615164100800_ref050","volume-title":"Advances in Neural Information Processing Systems","author":"Dosovitskiy","year":"2016"},{"key":"2026032615164100800_ref051","first-page":"2758","article-title":"Flownet: Learning optical flow with convolutional networks","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Dosovitskiy","year":"2015"},{"key":"2026032615164100800_ref052","article-title":"Lossy image compression with quantized hierarchical vaes","volume-title":"arXiv preprint arXiv:2208. F180313056","author":"Duan","year":"2022"},{"key":"2026032615164100800_ref053","article-title":"Lossy compression for lossless prediction","volume-title":"Neural Information Processing Systems","author":"Dubois","year":"2021"},{"key":"2026032615164100800_ref054","article-title":"Asymmetric numeral systems","volume-title":"arXiv preprint arXiv: 0902.0271","author":"Duda","year":"2009"},{"key":"2026032615164100800_ref055","doi-asserted-by":"crossref","first-page":"2959","DOI":"10.1109\/26.477498","article-title":"Image quality measures and their performance","volume":"43","author":"Eskicioglu","year":"1995","journal-title":"IEEE Trans. Communications"},{"key":"2026032615164100800_ref056","first-page":"12 873","article-title":"Taming transformers for high-resolution image synthesis","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Esser","year":"2021"},{"key":"2026032615164100800_ref057","volume-title":"Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding","author":"Flamich","year":"2020"},{"key":"2026032615164100800_ref058","first-page":"6548","volume-title":"Proceedings of the 39th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","author":"Flamich","year":"2022"},{"key":"2026032615164100800_ref059","volume-title":"Bayesian networks for pattern classification, data compression, and channel coding","author":"Frey","year":"1998"},{"issue":"2_and_3","key":"2026032615164100800_ref060","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1093\/comjnl\/40.2_and_3.157","article-title":"Efficient stochastic source coding and an application to a bayesian network source model","volume":"40","author":"Frey","year":"1997","journal-title":"The Computer Journal"},{"key":"2026032615164100800_ref061","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1049\/el:19900310","article-title":"Artificial neural network for image compression","volume":"26","author":"Sicuranza","year":"1990","journal-title":"Electronics Letters"},{"key":"2026032615164100800_ref062","doi-asserted-by":"crossref","unstructured":"L. A.\n              Gatys\n            , A. S.Ecker, and M.Bethge, \u201cImage style transfer using convolutional neural networks,\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2016. URL: http:\/\/www.cv-foundation.org\/openaccess\/content_cvpr_2016\/html\/Gatys_Image_Style_Transfer_CVPR_2016_paper.html.","DOI":"10.1109\/CVPR.2016.265"},{"key":"2026032615164100800_ref063","volume-title":"Vector quantization and signal compression","author":"Gersho","year":"2012"},{"key":"2026032615164100800_ref064","article-title":"Feedback recurrent autoencoder for video compression","volume-title":"Proceedings of the Asian Conference on Computer Vision","author":"Golinski","year":"2020"},{"key":"2026032615164100800_ref065","article-title":"Generative Adversarial Nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref066","volume-title":"Deep learning","author":"Goodfellow","year":"2016"},{"issue":"5","key":"2026032615164100800_ref067","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1109\/79.952802","article-title":"Theoretical foundations of transform coding","volume":"18","author":"Goyal","year":"2001","journal-title":"IEEE Signal Processing Magazine"},{"issue":"4","key":"2026032615164100800_ref068","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1109\/18.850706","article-title":"Transform coding with backward adaptive updates","volume":"46","author":"Goyal","year":"2000","journal-title":"IEEE Transactions on Information Theory"},{"issue":"6","key":"2026032615164100800_ref069","doi-asserted-by":"crossref","first-page":"2325","DOI":"10.1109\/18.720541","article-title":"Quantization","volume":"44","author":"Gray","year":"1998","journal-title":"IEEE transactions on information theory"},{"key":"2026032615164100800_ref070","first-page":"3549","article-title":"Towards conceptual compression","volume":"29","author":"Gregor","year":"2016","journal-title":"Advances In Neural Information Processing Systems"},{"key":"2026032615164100800_ref071","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4643.001.0001","volume-title":"The minimum description length principle","author":"Gr\u00fcnwald","year":"2007"},{"key":"2026032615164100800_ref072","first-page":"1","volume-title":"2019 Picture Coding Symposium (PCS)","author":"Guarda","year":"2019"},{"key":"2026032615164100800_ref073","first-page":"7033","article-title":"Video compression with rate-distortion autoencoders","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Habibian","year":"2019"},{"key":"2026032615164100800_ref074","article-title":"Deep generative video compression","volume-title":"Neural Information Processing Systems","author":"Han","year":"2019"},{"key":"2026032615164100800_ref075","first-page":"10","article-title":"The Communication Complexity of Correlation","volume-title":"Twenty-Second Annual IEEE Conference on Computational Complexity","author":"Harsha","year":"2007"},{"key":"2026032615164100800_ref076","article-title":"Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters","volume-title":"International Conference on Learning Representations","author":"Havasi","year":"2019"},{"key":"2026032615164100800_ref077","article-title":"Lossy image compression with normalizing flows","volume-title":"arXiv preprint arXiv: 2008.10486","author":"Helminger","year":"2020"},{"key":"2026032615164100800_ref078","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"2026032615164100800_ref079","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.specom.2011.09.004","article-title":"Speech Intelligibility Prediction using a Neurogram Similarity Index Measure","volume":"54","author":"Hines","year":"2012","journal-title":"Speech Communication"},{"key":"2026032615164100800_ref080","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0054-9","article-title":"ViSQOL: an objective speech quality model","volume-title":"EURASIP Journal on Audio, Speech, and Music Processing","author":"Hines","year":"2015"},{"key":"2026032615164100800_ref081","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/168304.168306","article-title":"Keeping the neural networks simple by minimizing the description length of the weights","volume-title":"Proceedings of the sixth annual conference on Computational learning theory","author":"Hinton","year":"1993"},{"key":"2026032615164100800_ref082","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"2026032615164100800_ref083","first-page":"3874","article-title":"Compression with flows via local bits-back coding","volume-title":"Advances in Neural Information Processing Systems","author":"Ho","year":"2019"},{"issue":"8","key":"2026032615164100800_ref084","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"issue":"4","key":"2026032615164100800_ref085","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/TNN.2004.828762","article-title":"Variational learning and bits-back coding: An information-theoretic view to bayesian learning","volume":"15","author":"Honkela","year":"2004","journal-title":"IEEE transactions on Neural Networks"},{"key":"2026032615164100800_ref086","article-title":"Autoregressive diffusion models","volume-title":"arXiv preprint arXiv:2110.02037","author":"Hoogeboom","year":"2021"},{"key":"2026032615164100800_ref087","first-page":"12 134","article-title":"Integer discrete flows and lossless compression","volume-title":"Advances in Neural Information Processing Systems","author":"Hoogeboom","year":"2019"},{"issue":"22","key":"2026032615164100800_ref088","doi-asserted-by":"crossref","first-page":"2213","DOI":"10.1016\/j.visres.2010.07.025","article-title":"Lower bounds on the redundancy of natural images","volume":"50","author":"Hosseini","year":"2010","journal-title":"Vision Research"},{"key":"2026032615164100800_ref089","first-page":"1313","article-title":"Octsqueeze: Octree-structured entropy model for lidar compression","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Huang","year":"2020"},{"issue":"4","key":"2026032615164100800_ref090","doi-asserted-by":"crossref","first-page":"040 901","DOI":"10.1117\/1.JEI.27.4.040901","article-title":"JPEG-1 standard 25 years: Past, present, and future reasons for a success","volume":"27","author":"Hudson","year":"2018","journal-title":"Journal of Electronic Imaging"},{"issue":"9","key":"2026032615164100800_ref091","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1109\/JRPROC.1952.273898","article-title":"A method for the construction of minimumredundancy codes","volume":"40","author":"Huffman","year":"1952","journal-title":"Proceedings of the IRE"},{"key":"2026032615164100800_ref092","volume-title":"Recommendation ITU-T T.81: Information technology \u2013 Digital compression and coding of continuous-tone still images \u2013 Requirements and guidelines","author":"ITU-T","year":"1992"},{"key":"2026032615164100800_ref093","volume-title":"Recommendation ITU-T T.800.2: Methods for objective and subjective assessment of speech and video quality","author":"ITU-T","year":"2016"},{"key":"2026032615164100800_ref094","doi-asserted-by":"crossref","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume-title":"Neural Computation","author":"Jacobs","year":"1991"},{"key":"2026032615164100800_ref095","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"arXiv preprint arXiv:1611.01144","author":"Jang","year":"2016"},{"issue":"9","key":"2026032615164100800_ref096","first-page":"737","article-title":"Image compression with neural networks\u2013a survey","volume":"14","author":"Jiang","year":"1999","journal-title":"Signal processing: image Communication"},{"issue":"1","key":"2026032615164100800_ref097","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/TNNLS.2018.2829819","article-title":"Deep cnn-based blind image quality predictor","volume":"30","author":"Kim","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2026032615164100800_ref098","first-page":"2678","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2018"},{"key":"2026032615164100800_ref099","article-title":"Auto-encoding variational Bayes","volume-title":"International Conference on Learning Representations","author":"Kingma","year":"2014"},{"key":"2026032615164100800_ref100","first-page":"10 215","article-title":"Glow: Generative Flow with Invertible 1x1 Convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref101","article-title":"Improved variational inference with inverse autoregressive flow","volume":"29","author":"Kingma","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"2026032615164100800_ref102","unstructured":"B.\n              Knoll\n            \n          , Cmix. URL: https:\/\/www.byronknoll.com\/cmix.html."},{"key":"2026032615164100800_ref103","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky","year":"2012"},{"key":"2026032615164100800_ref104","article-title":"The Neural Autoregressive Distribution Estimator","volume-title":"Proceedings of the 14th International Conference on Artificial Intelligence and Statistics","author":"Larochelle","year":"2011"},{"key":"2026032615164100800_ref105","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.19","article-title":"Photo-realistic single image super-resolution using a generative adversarial network","volume-title":"CVPR","author":"Ledig","year":"2017"},{"key":"2026032615164100800_ref106","article-title":"Context-adaptive entropy model for end-to-end optimized image compression","volume-title":"International Conference on Learning Representations","author":"Lee","year":"2019"},{"key":"2026032615164100800_ref107","doi-asserted-by":"crossref","DOI":"10.1109\/ISIT.2017.8006596","article-title":"Strong Functional Representation Lemma and Applications to Coding Theorems","volume-title":"IEEE International Symposium on Information Theory","author":"Li","year":"2017"},{"key":"2026032615164100800_ref108","volume-title":"Learning convolutional networks for content-weighted image compression","author":"Li","year":"2017"},{"key":"2026032615164100800_ref109","unstructured":"Z.\n              Li\n            , A.Aaron, I.Katsavounidis, A.Moorthy, and M.Manohara, Toward a practical perceptual video quality metric, 2016. URL: https:\/\/netflixtechblog.com\/toward-a-practical-perceptual-video-quality-metric-653f208b9652."},{"key":"2026032615164100800_ref110","article-title":"Lossless compression with probabilistic circuits","volume-title":"International Conference on Learning Representations","author":"Liu","year":"2022"},{"issue":"1","key":"2026032615164100800_ref111","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3368405","article-title":"Deep learning-based video coding: A review and a case study","volume":"53","author":"Liu","year":"2020","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2026032615164100800_ref112","article-title":"Non-local attention optimized deep image compression","volume-title":"arXiv preprint arXiv:1904.09757","author":"Liu","year":"2019"},{"key":"2026032615164100800_ref113","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2013.5","article-title":"Visual quality assessment: Recent developments, coding applications and future trends","volume":"2","author":"Liu","year":"2013","journal-title":"APSIPA Transactions on Signal and Information Processing"},{"issue":"2","key":"2026032615164100800_ref114","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in pcm","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE transactions on information theory"},{"key":"2026032615164100800_ref115","first-page":"11 006","article-title":"Dvc: An end-to-end deep video compression framework","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Lu","year":"2019"},{"key":"2026032615164100800_ref116","article-title":"An end-to-end learning framework for video compression","volume-title":"IEEE transactions on pattern analysis and machine intelligence","author":"Lu","year":"2020"},{"issue":"6","key":"2026032615164100800_ref117","doi-asserted-by":"crossref","first-page":"1683","DOI":"10.1109\/TCSVT.2019.2910119","article-title":"Image and video compression with neural networks: A review","volume":"30","author":"Ma","year":"2019","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2026032615164100800_ref118","volume-title":"Information theory, inference and learning algorithms","author":"MacKay","year":"2003"},{"key":"2026032615164100800_ref119","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"arXiv preprint arXiv:1611.00712","author":"Maddison","year":"2016"},{"key":"2026032615164100800_ref120","unstructured":"M.\n              Mahoney\n            \n          , Large Text Compression Benchmark. URL: http:\/\/mattmahoney.net\/dc\/text.html."},{"key":"2026032615164100800_ref121","doi-asserted-by":"publisher","first-page":"2813","DOI":"10.1109\/ICCV.2017.304","article-title":"Least squares generative adversarial networks","volume-title":"IEEE International Conference on Computer Vision (ICCV)","author":"Mao","year":"2017"},{"key":"2026032615164100800_ref122","first-page":"24","article-title":"Range encoding: An algorithm for removing redundancy from a digitised message","volume":"1979","author":"Martin","year":"1979","journal-title":"Video and Data Recording Conference, Southampton"},{"key":"2026032615164100800_ref123","article-title":"Supervised compression for resource-constrained edge computing systems","volume-title":"arXiv preprint arXiv:2108.11898","author":"Matsubara","year":"2021"},{"key":"2026032615164100800_ref124","first-page":"4394","article-title":"Conditional probability models for deep image compression","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Mentzer","year":"2018"},{"key":"2026032615164100800_ref125","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.01088","article-title":"Practical full resolution learned lossless image compression","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Mentzer","year":"2019"},{"key":"2026032615164100800_ref126","article-title":"Vct: A video compression transformer","volume-title":"arXiv preprint arXiv:2206.07307","author":"Mentzer","year":"2022"},{"key":"2026032615164100800_ref127","article-title":"High-fidelity generative image compression","volume":"33","author":"Mentzer","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref128","article-title":"Glicbawls \u2013 Grey Level Image Compression By Adaptive Weighted Least Squares","volume-title":"Data Compression Conference","author":"Meyer","year":"2001"},{"issue":"1","key":"2026032615164100800_ref129","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3503250","article-title":"Nerf: Representing scenes as neural radiance fields for view synthesis","volume":"65","author":"Mildenhall","year":"2021","journal-title":"Communications of the ACM"},{"key":"2026032615164100800_ref130","article-title":"Divergence measures and message passing","volume-title":"Microsoft Research, Tech. Rep. TR-2005-173","author":"Minka","year":"2005"},{"key":"2026032615164100800_ref131","article-title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","volume":"31","author":"Minnen","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref132","doi-asserted-by":"crossref","DOI":"10.1109\/ICIP40778.2020.9190935","article-title":"Channel-wise autoregressive entropy models for learned image compression","volume-title":"IEEE International Conference on Image Processing (ICIP)","author":"Minnen","year":"2020"},{"key":"2026032615164100800_ref133","volume-title":"Current Frontiers In Neural Image Compression: The Rate-Distortion-Computation Trade-Off And Optimizing For Subjective Visual Quality","author":"Minnen","year":"2021"},{"issue":"3","key":"2026032615164100800_ref134","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a \u201cCompletely Blind\u201d Image Quality Analyzer","volume":"20","author":"Mittal","year":"2013","journal-title":"IEEE Signal Processing Letters"},{"key":"2026032615164100800_ref135","unstructured":"D.\n              Mukherjee\n            \n          , \u201cChallenges in incorporating ML in a mainstream nextgen video codec,\u201d CLIC Workshop and Challenge on Learned Image Compression, 2022. URL: https:\/\/storage.googleapis.com\/clic2022_public\/slides\/Challenges%20in%20incorporating%20ML%20in%20a%20practical%20Nextgen%20Video%20Codec.pdf."},{"key":"2026032615164100800_ref136","doi-asserted-by":"crossref","DOI":"10.1145\/3528223.3530127","article-title":"Instant neural graphics primitives with a multiresolution hash encoding","volume-title":"arXiv preprint arXiv:2201.05989","author":"M\u00fcller","year":"2022"},{"issue":"2","key":"2026032615164100800_ref137","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1214\/08-AOS595","article-title":"On surrogate loss functions and f-divergences","volume":"37","author":"Nguyen","year":"2009","journal-title":"The Annals of Statistics"},{"key":"2026032615164100800_ref138","article-title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","volume":"29","author":"Nowozin","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref139","unstructured":"A.\n              van den Oord\n            , S.Dieleman, H.Zen, K.Simonyan, O.Vinyals, A.Graves, N.Kalchbrenner, A. W.Senior, and K.Kavukcuoglu, \u201cWaveNet: A Generative Model for Raw Audio,\u201d CoRR, vol. abs\/1609.03499, 2016. URL: http:\/\/arxiv.org\/abs\/1609.03499."},{"key":"2026032615164100800_ref140","article-title":"Pixel Recurrent Neural Networks","volume-title":"Proceedings of the 33rd International Conference on Machine Learning","author":"van den Oord","year":"2016"},{"key":"2026032615164100800_ref141","first-page":"4790","article-title":"Conditional Image Generation with PixelCNN Decoders","volume":"29","author":"van den Oord","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref142","article-title":"Neural discrete representation learning","author":"Oord","year":"2017"},{"key":"2026032615164100800_ref143","first-page":"4055","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Parmar","year":"2018"},{"key":"2026032615164100800_ref144","article-title":"Einsum networks: Fast and scalable learning of tractable probabilistic circuits","volume-title":"International Conference on Machine Learning","author":"Peharz","year":"2020"},{"key":"2026032615164100800_ref145","article-title":"Constrained differential optimization for neural networks","volume-title":"California Institute of Technology, Tech. Rep","author":"Platt","year":"1988"},{"key":"2026032615164100800_ref146","doi-asserted-by":"crossref","DOI":"10.3389\/frsip.2022.846972","article-title":"Survey on deep learning-based point cloud compression","volume-title":"Frontiers in Signal Processing","author":"Quach","year":"2022"},{"key":"2026032615164100800_ref147","doi-asserted-by":"crossref","first-page":"4320","DOI":"10.1109\/ICIP.2019.8803413","volume-title":"2019 IEEE international conference on image processing (ICIP)","author":"Quach","year":"2019"},{"key":"2026032615164100800_ref148","first-page":"1","volume-title":"2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)","author":"Quach","year":"2020"},{"key":"2026032615164100800_ref149","first-page":"8821","volume-title":"International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"2026032615164100800_ref150","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"International Conference on Machine Learning","author":"Rezende","year":"2014"},{"key":"2026032615164100800_ref151","first-page":"1530","volume-title":"International conference on machine learning","author":"Rezende","year":"2015"},{"key":"2026032615164100800_ref152","article-title":"Real-time adaptive image compression","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Rippel","year":"2017"},{"key":"2026032615164100800_ref153","first-page":"3454","article-title":"Learned video compression","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Rippel","year":"2019"},{"issue":"2","key":"2026032615164100800_ref154","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1147\/rd.232.0149","article-title":"Arithmetic coding","volume":"23","author":"Rissanen","year":"1979","journal-title":"IBM Journal of research and development"},{"key":"2026032615164100800_ref155","doi-asserted-by":"crossref","DOI":"10.1109\/TIT.1962.1057702","article-title":"Picture Coding Using Pseudo-Random Noise","volume-title":"IRE Transactions on Information Theory","author":"Roberts","year":"1962"},{"key":"2026032615164100800_ref156","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW50498.2020.00091","volume-title":"Lossy compression with distortion constrained optimization","author":"van Rozendaal","year":"2020"},{"key":"2026032615164100800_ref157","article-title":"Improving lossless compression rates via monte carlo bits-back coding","volume-title":"International Conference on Machine Learning","author":"Ruan","year":"2021"},{"key":"2026032615164100800_ref158","author":"Rumelhart","year":"1985"},{"key":"2026032615164100800_ref159","article-title":"Palette: Image-to-Image Diffusion Models","volume-title":"CoRR","author":"Saharia","year":"2021"},{"key":"2026032615164100800_ref160","article-title":"PixelCNN++: A pixelcnn implementation with discretized logistic mixture likelihood and other modifications","volume-title":"International Conference on Learning Representations","author":"Salimans","year":"2017"},{"key":"2026032615164100800_ref161","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1109\/PCS.2018.8456298","article-title":"Generative compression","volume-title":"2018 Picture Coding Symposium (PCS)","author":"Santurkar","year":"2018"},{"key":"2026032615164100800_ref162","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/B978-0-12-415796-5.00010-7","volume-title":"Introduction to Data Compression (Fourth Edition), ser. The Morgan Kaufmann Series in Multimedia Information and Systems","author":"Sayood","year":"2012","edition":"4th"},{"key":"2026032615164100800_ref163","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A Mathematical Theory of Communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell System Technical Journal"},{"key":"2026032615164100800_ref164","first-page":"142","article-title":"Coding theorems for a discrete source with a fidelity criterion","volume":"4","author":"Shannon","year":"1959","journal-title":"IRE Nat. Conv. Rec"},{"issue":"11","key":"2026032615164100800_ref165","doi-asserted-by":"publisher","first-page":"3440","DOI":"10.1109\/TIP.2006.881959","article-title":"A statistical evaluation of recent full reference image quality assessment algorithms","volume":"15","author":"Sheikh","year":"2006","journal-title":"IEEE Transactions on Image Processing"},{"key":"2026032615164100800_ref166","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"International Conference on Learning Representations","author":"Simonyan","year":"2015"},{"key":"2026032615164100800_ref167","first-page":"3349","volume-title":"ICIP","author":"Singh","year":"2020"},{"key":"2026032615164100800_ref168","first-page":"2256","volume-title":"International Conference on Machine Learning","author":"Sohl-Dickstein","year":"2015"},{"key":"2026032615164100800_ref169","volume-title":"Advances in Neural Information Processing Systems","author":"S\u00f8nderby","year":"2016"},{"key":"2026032615164100800_ref170","first-page":"35","article-title":"Image data compression using a neural network model","volume":"2","author":"Sonehara","year":"1989","journal-title":"International 1989 Joint Conference on Neural Networks"},{"key":"2026032615164100800_ref171","doi-asserted-by":"crossref","DOI":"10.1109\/TIT.2016.2529657","article-title":"The likelihood encoder for lossy compression","volume":"62","author":"Song","year":"2016","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026032615164100800_ref172","article-title":"On integral probability metrics, \u03c6-divergences and binary classification","volume-title":"arXiv","author":"Sriperumbudur","year":"2009"},{"key":"2026032615164100800_ref173","article-title":"Blockwise parallel decoding for deep autoregressive models","volume":"31","author":"Stern","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref174","doi-asserted-by":"crossref","unstructured":"K.\n              Storrs\n            , S. V.Leuven, S.Kojder, L.Theis, and F.Husz\u00e1r, \u201cAdaptive paired-comparison method for subjective video quality assessment on mobile devices,\u201d in Picture Coding Symposium, 2018. URL: https:\/\/arxiv.org\/abs\/1807.02175.","DOI":"10.1109\/PCS.2018.8456273"},{"key":"2026032615164100800_ref175","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1002\/(SICI)1234-981X(199707)5:3<305::AID-EURO184>3.0.CO;2-4","article-title":"Improving ratings: audit in the British University system","volume":"5","author":"Strathern","year":"1997","journal-title":"European Review"},{"issue":"5","key":"2026032615164100800_ref176","doi-asserted-by":"publisher","first-page":"1365","DOI":"10.1109\/18.532878","article-title":"Efficient scalar quantization of exponential and laplacian random variables","volume":"42","author":"Sullivan","year":"1996","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026032615164100800_ref177","article-title":"Rethinking the inception architecture for computer vision","volume":"1512.00567","author":"Szegedy","year":"2015","journal-title":"arXiv"},{"key":"2026032615164100800_ref178","first-page":"1293","article-title":"Deep implicit volume compression","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Tang","year":"2020"},{"key":"2026032615164100800_ref179","unstructured":"L.\n              Theis\n             and E.Agustsson, \u201cOn the advantages of stochastic encoders,\u201d 2021. URL: https:\/\/arxiv.org\/abs\/2102.09270."},{"key":"2026032615164100800_ref180","article-title":"Generative image modeling using spatial LSTMs","volume":"28","author":"Theis","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref181","unstructured":"L.\n              Theis\n             and J.Ho, \u201cImportance weighted compression,\u201d in Neural Compression Workshop at ICLR 2021, 2021. URL: https:\/\/openreview.net\/forum?id=n6skss_9-v3."},{"issue":"7","key":"2026032615164100800_ref182","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0039857","article-title":"Mixtures of conditional Gaussian scale mixtures applied to multiscale image representations","volume":"7","author":"Theis","year":"2012","journal-title":"PLoS ONE"},{"key":"2026032615164100800_ref183","unstructured":"L.\n              Theis\n            , A.van den Oord, and M.Bethge, \u201cA note on the evaluation of generative models,\u201d in International Conference on Learning Representations, Apr. 2016. URL: http:\/\/arxiv.org\/abs\/1511.01844."},{"key":"2026032615164100800_ref184","article-title":"Lossy Image Compression with Compressive Autoencoders","volume-title":"International Conference on Learning Representations","author":"Theis","year":"2017"},{"key":"2026032615164100800_ref185","volume-title":"Lossy compression with gaussian diffusion","author":"Theis","year":"2022"},{"key":"2026032615164100800_ref186","article-title":"Algorithms for the communication of samples","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Theis","year":"2021"},{"key":"2026032615164100800_ref187","article-title":"The information bottleneck method","volume-title":"arXiv preprint physics\/0004057","author":"Tishby","year":"2000"},{"key":"2026032615164100800_ref188","article-title":"Variable rate image compression with recurrent neural networks","volume-title":"International Conference on Learning Representations","author":"Toderici","year":"2016"},{"key":"2026032615164100800_ref189","first-page":"5306","article-title":"Full resolution image compression with recurrent neural networks","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Toderici","year":"2017"},{"key":"2026032615164100800_ref190","article-title":"Towards image understanding from deep compression without decoding","volume-title":"arXiv preprint arXiv:1803.06131","author":"Torfason","year":"2018"},{"key":"2026032615164100800_ref191","article-title":"A tutorial on the range variant of asymmetric numeral systems","volume-title":"arXiv preprint arXiv:2001.09186","author":"Townsend","year":"2020"},{"key":"2026032615164100800_ref192","article-title":"Hilloc: Lossless image compression with hierarchical latent variable models","volume-title":"arXiv preprint arXiv:1912.09953","author":"Townsend","year":"2019"},{"key":"2026032615164100800_ref193","article-title":"Practical lossless compression with latent variables using bits back coding","volume-title":"arXiv preprint arXiv:1901.04866","author":"Townsend","year":"2019"},{"key":"2026032615164100800_ref194","article-title":"Lossless compression with state space models using bits back coding","volume-title":"arXiv preprint arXiv:2103.10150","author":"Townsend","year":"2021"},{"key":"2026032615164100800_ref195","first-page":"14 719","article-title":"Discrete flows: Invertible generative models of discrete data","volume-title":"Advances in Neural Information Processing Systems","author":"Tran","year":"2019"},{"key":"2026032615164100800_ref196","doi-asserted-by":"publisher","first-page":"2089","DOI":"10.1109\/ICIP42928.2021.9506497","article-title":"Comprehensive comparisons of uniform quantizers for deep image compression","volume-title":"2021 IEEE International Conference on Image Processing (ICIP)","author":"Tsubota","year":"2021"},{"key":"2026032615164100800_ref197","article-title":"RNADE: the real-valued neural autoregressive density-estimator","volume":"26","author":"Uria","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref198","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032615164100800_ref199","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1109\/DCC50243.2021.00022","volume-title":"2021 Data Compression Conference (DCC)","author":"Wagner","year":"2021"},{"key":"2026032615164100800_ref200","first-page":"72","volume-title":"International Conference on Computing and Information","author":"Wallace","year":"1990"},{"key":"2026032615164100800_ref201","doi-asserted-by":"publisher","first-page":"1398","DOI":"10.1109\/ACSSC.2003.1292216","article-title":"Multiscale structural similarity for image quality assessment","volume":"2","author":"Wang","year":"2003","journal-title":"The Thrity-Seventh Asilomar Conference on Signals, Systems Computers, 2003"},{"issue":"3","key":"2026032615164100800_ref202","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1022672621406","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Machine learning"},{"key":"2026032615164100800_ref203","first-page":"416","article-title":"Video compression through image interpolation","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Wu","year":"2018"},{"key":"2026032615164100800_ref204","first-page":"901","volume-title":"ICIP","author":"Wu","year":"1998"},{"key":"2026032615164100800_ref205","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1145\/3474085.3475213","article-title":"Enhanced invertible encoding for learned image compression","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia","author":"Xie","year":"2021"},{"key":"2026032615164100800_ref206","article-title":"Learning for video compression with recurrent auto-encoder and recurrent probability model","volume-title":"IEEE Journal of Selected Topics in Signal Processing","author":"Yang","year":"2020"},{"key":"2026032615164100800_ref207","volume-title":"Lossy image compression with conditional diffusion models","author":"Yang","year":"2022"},{"key":"2026032615164100800_ref208","article-title":"Hierarchical autoregressive modeling for neural video compression","volume-title":"International Conference on Learning Representations","author":"Yang","year":"2020"},{"key":"2026032615164100800_ref209","article-title":"Improving inference for neural image compression","volume-title":"Neural Information Processing Systems (NeurIPS), 2020","author":"Yang","year":"2020"},{"key":"2026032615164100800_ref210","article-title":"Variational Bayesian Quantization","volume-title":"International Conference on Machine Learning","author":"Yang","year":"2020"},{"key":"2026032615164100800_ref211","article-title":"Towards empirical sandwich bounds on the rate-distortion function","volume-title":"International Conference on Learnning Representations","author":"Yang","year":"2022"},{"key":"2026032615164100800_ref212","first-page":"5752","article-title":"Plenoc-trees for real-time rendering of neural radiance fields","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Yu","year":"2021"},{"key":"2026032615164100800_ref213","article-title":"Vector-quantized image modeling with improved vqgan","volume-title":"arXiv preprint arXiv:2110.04627","author":"Yu","year":"2021"},{"key":"2026032615164100800_ref214","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume-title":"arXiv preprint arXiv:2206.10789","author":"Yu","year":"2022"},{"key":"2026032615164100800_ref215","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139045520","volume-title":"Lattice Coding for Signals and Networks","author":"Zamir","year":"2014"},{"issue":"2","key":"2026032615164100800_ref216","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1109\/18.119699","article-title":"On universal quantization by randomized uniform\/lattice quantizers","volume":"38","author":"Zamir","year":"1992","journal-title":"IEEE Transactions on Information Theory"},{"issue":"8","key":"2026032615164100800_ref217","doi-asserted-by":"crossref","first-page":"2008","DOI":"10.1109\/TPAMI.2018.2889774","article-title":"Advances in variational inference","volume":"41","author":"Zhang","year":"2018","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"8","key":"2026032615164100800_ref218","doi-asserted-by":"publisher","first-page":"2579","DOI":"10.1109\/TIP.2015.2426416","article-title":"A feature-enriched completely blind image quality evaluator","volume":"24","author":"Zhang","year":"2015","journal-title":"IEEE Transactions on Image Processing"},{"key":"2026032615164100800_ref219","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1109\/CVPR.2018.00068","article-title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhang","year":"2018"},{"key":"2026032615164100800_ref220","article-title":"Variational Autoencoder for Low Bit-rate Image Compression","volume-title":"Challenge on Learned Image Compression","author":"Zhou","year":"2018"},{"issue":"4","key":"2026032615164100800_ref221","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Transactions on Image Processing"},{"key":"2026032615164100800_ref222","article-title":"Transformer-based transform coding","volume-title":"International Conference on Learning Representations","author":"Zhu","year":"2021"},{"issue":"3","key":"2026032615164100800_ref223","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1109\/TIT.1985.1057034","article-title":"On universal quantization","volume":"31","author":"Ziv","year":"1985","journal-title":"IEEE Transactions on Information Theory"},{"issue":"3","key":"2026032615164100800_ref224","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1109\/TIT.1977.1055714","article-title":"A universal algorithm for sequential data compression","volume":"23","author":"Ziv","year":"1977","journal-title":"IEEE Transactions on information theory"}],"container-title":["Foundations and Trends\u00ae in Computer Graphics and Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftcgv\/article-pdf\/15\/2\/113\/10865074\/0600000107en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftcgv\/article-pdf\/15\/2\/113\/10865074\/0600000107en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:17:21Z","timestamp":1774552641000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftcgv\/article\/15\/2\/113\/1319350\/An-Introduction-to-Neural-Data-Compression"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,25]]},"references-count":224,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,4,25]]}},"URL":"https:\/\/doi.org\/10.1561\/0600000107","relation":{},"ISSN":["1572-2740","1572-2759"],"issn-type":[{"value":"1572-2740","type":"print"},{"value":"1572-2759","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,25]]}}}