{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:51:22Z","timestamp":1772905882452,"version":"3.50.1"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732416","type":"print"},{"value":"9783031732423","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73242-3_27","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"480-496","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Bidirectional Stereo Image Compression with\u00a0Cross-Dimensional Entropy Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6502-368X","authenticated-orcid":false,"given":"Zhening","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3194-7518","authenticated-orcid":false,"given":"Xinjie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8836-1430","authenticated-orcid":false,"given":"Jiawei","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9503-2464","authenticated-orcid":false,"given":"Zehong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5222-1898","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"issue":"2","key":"27_CR1","doi-asserted-by":"publisher","first-page":"28","DOI":"10.3390\/computers11020028","volume":"11","author":"F Arena","year":"2022","unstructured":"Arena, F., Collotta, M., Pau, G., Termine, F.: An overview of augmented reality. Computers 11(2), 28 (2022)","journal-title":"Computers"},{"issue":"2","key":"27_CR2","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1109\/JSTSP.2020.3034501","volume":"15","author":"J Ball\u00e9","year":"2020","unstructured":"Ball\u00e9, J., et al.: Nonlinear transform coding. IEEE J. Sel. Top. Signal Process. 15(2), 339\u2013353 (2020)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"27_CR3","unstructured":"Ball\u00e9, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. arXiv preprint arXiv:1611.01704 (2016)"},{"key":"27_CR4","unstructured":"Ball\u00e9, J., Minnen, D., Singh, S., Hwang, S.J., Johnston, N.: Variational image compression with a scale hyperprior. arXiv preprint arXiv:1802.01436 (2018)"},{"key":"27_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-019-2803-x","volume":"63","author":"W Bao","year":"2020","unstructured":"Bao, W., Wang, W., Xu, Y., Guo, Y., Hong, S., Zhang, X.: Instereo2k: a large real dataset for stereo matching in indoor scenes. Sci. China Inf. Sci. 63, 1\u201311 (2020)","journal-title":"Sci. China Inf. Sci."},{"key":"27_CR6","unstructured":"Bellard, F.: BPG image format. Website (2014). https:\/\/bellard.org\/bpg\/"},{"key":"27_CR7","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/978-94-011-5014-9_13","volume-title":"Learn. Graph. Models","author":"CM Bishop","year":"1998","unstructured":"Bishop, C.M.: Latent variable models. In: Jordan, M.I. (ed.) Learn. Graph. Models, vol. 89, pp. 371\u2013403. Springer, Dordrecht (1998). https:\/\/doi.org\/10.1007\/978-94-011-5014-9_13"},{"key":"27_CR8","unstructured":"Bjontegaard, G.: Calculation of average PSNR differences between RD-curves. ITU SG16 Doc. VCEG-M33 (2001)"},{"issue":"10","key":"27_CR9","doi-asserted-by":"publisher","first-page":"3736","DOI":"10.1109\/TCSVT.2021.3101953","volume":"31","author":"B Bross","year":"2021","unstructured":"Bross, B., et al.: Overview of the versatile video coding (VVC) standard and its applications. IEEE Trans. Circuits Syst. Video Technol. 31(10), 3736\u20133764 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Sun, H., Takeuchi, M., Katto, J.: Learned image compression with discretized Gaussian mixture likelihoods and attention modules. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Deng, X., Deng, Y., Yang, R., Yang, W., Timofte, R., Xu, M.: MASIC: deep mask stereo image compression. IEEE Trans. Circuits Syst. Video Technol. (2023)","DOI":"10.1109\/TCSVT.2023.3253702"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Deng, X., et al.: Deep homography for efficient stereo image compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1492\u20131501 (2021)","DOI":"10.1109\/CVPR46437.2021.00154"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"He, D., Yang, Z., Peng, W., Ma, R., Qin, H., Wang, Y.: ELIC: efficient learned image compression with unevenly grouped space-channel contextual adaptive coding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5718\u20135727 (2022)","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"He, D., Zheng, Y., Sun, B., Wang, Y., Qin, H.: Checkerboard context model for efficient learned image compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14771\u201314780 (2021)","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Hu, Y., Yang, W., Liu, J.: Coarse-to-fine hyper-prior modeling for learned image compression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11013\u201311020 (2020)","DOI":"10.1609\/aaai.v34i07.6736"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, W., Yang, J., Zhai, Y., Ning, P., Gao, F., Wang, R.: MLIC: multi-reference entropy model for learned image compression. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 7618\u20137627 (2023)","DOI":"10.1145\/3581783.3611694"},{"key":"27_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.image.2017.10.008","volume":"61","author":"A Kadaikar","year":"2018","unstructured":"Kadaikar, A., Dauphin, G., Mokraoui, A.: Joint disparity and variable size-block optimization algorithm for stereoscopic image compression. Signal Process. Image Commun. 61, 1\u20138 (2018)","journal-title":"Signal Process. Image Commun."},{"key":"27_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Lei, J., Liu, X., Peng, B., Jin, D., Li, W., Gu, J.: Deep stereo image compression via bi-directional coding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19669\u201319678 (2022)","DOI":"10.1109\/CVPR52688.2022.01905"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, S., Urtasun, R.: DSIC: deep stereo image compression. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00323"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Liu, J., Sun, H., Katto, J.: Learned image compression with mixed transformer-CNN architectures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14388\u201314397 (2023)","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Ren, J., Zhang, J., Liu, J., Lin, M.: Visually imbalanced stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2029\u20132038 (2020)","DOI":"10.1109\/CVPR42600.2020.00210"},{"key":"27_CR24","unstructured":"Minnen, D., Ball\u00e9, J., Toderici, G.D.: Joint autoregressive and hierarchical priors for learned image compression. In: Advances in neural information processing systems, vol. 31 (2018)"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Minnen, D., Singh, S.: Channel-wise autoregressive entropy models for learned image compression. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 3339\u20133343. IEEE (2020)","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"27_CR26","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1007\/978-3-031-19797-0_32","volume-title":"ECCV 2022","author":"G Pan","year":"2022","unstructured":"Pan, G., Lu, G., Hu, Z., Xu, D.: Content adaptive latents and decoder for neural image compression. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13678, pp. 556\u2013573. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19797-0_32"},{"key":"27_CR27","unstructured":"Shen, Z., Zhang, M., Zhao, H., Yi, S., Li, H.: Efficient attention: attention with linear complexities. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3531\u20133539 (2021)"},{"issue":"5","key":"27_CR28","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/79.952804","volume":"18","author":"A Skodras","year":"2001","unstructured":"Skodras, A., Christopoulos, C., Ebrahimi, T.: The JPEG 2000 still image compression standard. IEEE Signal Process. Mag. 18(5), 36\u201358 (2001)","journal-title":"IEEE Signal Process. Mag."},{"key":"27_CR29","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1007\/s11263-019-01287-w","volume":"128","author":"X Song","year":"2020","unstructured":"Song, X., Zhao, X., Fang, L., Hu, H., Yu, Y.: EdgeStereo: an effective multi-task learning network for stereo matching and edge detection. Int. J. Comput. Vis. 128, 910\u2013930 (2020)","journal-title":"Int. J. Comput. Vis."},{"issue":"12","key":"27_CR30","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","volume":"22","author":"GJ Sullivan","year":"2012","unstructured":"Sullivan, G.J., Ohm, J.R., Han, W.J., Wiegand, T.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circuits Syst. Video Technol. 22(12), 1649\u20131668 (2012)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"27_CR31","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/TCSVT.2015.2477935","volume":"26","author":"G Tech","year":"2015","unstructured":"Tech, G., Chen, Y., M\u00fcller, K., Ohm, J.R., Vetro, A., Wang, Y.K.: Overview of the multiview and 3D extensions of high efficiency video coding. IEEE Trans. Circuits Syst. Video Technol. 26(1), 35\u201349 (2015)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"27_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"4","key":"27_CR33","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1109\/JPROC.2010.2098830","volume":"99","author":"A Vetro","year":"2011","unstructured":"Vetro, A., Wiegand, T., Sullivan, G.J.: Overview of the stereo and multiview video coding extensions of the H.264\/MPEG-4 AVC standard. Proc. IEEE 99(4), 626\u2013642 (2011)","journal-title":"Proc. IEEE"},{"issue":"4","key":"27_CR34","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1145\/103085.103089","volume":"34","author":"GK Wallace","year":"1991","unstructured":"Wallace, G.K.: The JPEG still picture compression standard. Commun. ACM 34(4), 30\u201344 (1991)","journal-title":"Commun. ACM"},{"key":"27_CR35","unstructured":"Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thirty-Seventh Asilomar Conference on Signals, Systems & Computers, vol.\u00a02, pp. 1398\u20131402. IEEE (2003)"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"W\u00f6dlinger, M., Kotera, J., Keglevic, M., Xu, J., Sablatnig, R.: ECSIC: epipolar cross attention for stereo image compression. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3436\u20133445 (2024)","DOI":"10.1109\/WACV57701.2024.00340"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"W\u00f6dlinger, M., Kotera, J., Xu, J., Sablatnig, R.: SASIC: stereo image compression with latent shifts and stereo attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 661\u2013670 (2022)","DOI":"10.1109\/CVPR52688.2022.00074"},{"issue":"2","key":"27_CR38","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1109\/TITS.2019.2961120","volume":"22","author":"H Yin","year":"2020","unstructured":"Yin, H., Wang, Y., Tang, L., Ding, X., Huang, S., Xiong, R.: 3D lidar map compression for efficient localization on resource constrained vehicles. IEEE Trans. Intell. Transp. Syst. 22(2), 837\u2013852 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"27_CR39","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1109\/LSP.2020.2973813","volume":"27","author":"X Ying","year":"2020","unstructured":"Ying, X., Wang, Y., Wang, L., Sheng, W., An, W., Guo, Y.: A stereo attention module for stereo image super-resolution. IEEE Signal Process. Lett. 27, 496\u2013500 (2020)","journal-title":"IEEE Signal Process. Lett."},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Zhai, Y., Tang, L., Ma, Y., Peng, R., Wang, R.: Disparity-based stereo image compression with aligned cross-view priors. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 2351\u20132360 (2022)","DOI":"10.1145\/3503161.3548136"},{"key":"27_CR41","unstructured":"Zhang, X., Shao, J., Zhang, J.: LDMIC: learning-based distributed multi-view image coding. arXiv preprint arXiv:2301.09799 (2023)"},{"key":"27_CR42","unstructured":"Zhu, Y., Yang, Y., Cohen, T.: Transformer-based transform coding. In: International Conference on Learning Representations (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73242-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:38:54Z","timestamp":1730108334000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73242-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031732416","9783031732423"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73242-3_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}