{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:27:28Z","timestamp":1758126448080,"version":"3.40.3"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730290"},{"type":"electronic","value":"9783031730306"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"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\/978-3-031-73030-6_11","type":"book-chapter","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T16:56:38Z","timestamp":1732553798000},"page":"183-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Compensation Sampling for\u00a0Improved Convergence in\u00a0Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9167-7452","authenticated-orcid":false,"given":"Hui","family":"Lu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6342-428X","authenticated-orcid":false,"given":"Albert Ali","family":"Salah","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0843-7878","authenticated-orcid":false,"given":"Ronald","family":"Poppe","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"11_CR1","first-page":"9506","volume":"34","author":"D Arad Hudson","year":"2021","unstructured":"Arad Hudson, D., Zitnick, L.: Compositional transformers for scene generation. Adv. Neural. Inf. Process. Syst. 34, 9506\u20139520 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR2","unstructured":"Bansal, A., et al.: Cold diffusion: inverting arbitrary image transforms without noise. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"11_CR3","unstructured":"Bao, F., Li, C., Sun, J., Zhu, J., Zhang, B.: Estimating the optimal covariance with imperfect mean in diffusion probabilistic models. In: International Conference on Machine Learning, pp. 1555\u20131584. PMLR (2022)"},{"key":"11_CR4","unstructured":"Bao, F., Li, C., Zhu, J., Zhang, B.: Analytic-DPM: an analytic estimate of the optimal reverse variance in diffusion probabilistic models. In: International Conference on Learning Representations (2022)"},{"key":"11_CR5","unstructured":"Batzolis, G., Stanczuk, J., Sch\u00f6nlieb, C.B., Etmann, C.: Conditional image generation with score-based diffusion models. arXiv preprint arXiv:2111.13606 (2021)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Cheung, Y.M., Li, M., Zou, R.: Facial structure guided GAN for identity-preserved face image de-occlusion. In: International Conference on Multimedia Retrieval, pp. 46\u201354 (2021)","DOI":"10.1145\/3460426.3463642"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Choi, J., Lee, J., Shin, C., Kim, S., Kim, H., Yoon, S.: Perception prioritized training of diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11472\u201311481 (2022)","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"11_CR8","unstructured":"Daras, G., Delbracio, M., Talebi, H., Dimakis, A., Milanfar, P.: Soft Diffusion: Score matching with general corruptions. Transactions on Machine Learning Research (TMLR) (2023)"},{"key":"11_CR9","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Dong, J., Zhang, L., Zhang, H., Liu, W.: Occlusion-aware GAN for face de-occlusion in the wild. In: IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136 (2020)","DOI":"10.1109\/ICME46284.2020.9102788"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Fei, B., et al.: Generative diffusion prior for unified image restoration and enhancement. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9935\u20139946 (2023)","DOI":"10.1109\/CVPR52729.2023.00958"},{"key":"11_CR13","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems. vol.\u00a027 (2014)"},{"key":"11_CR14","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"11_CR15","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Jain, J., Zhou, Y., Yu, N., Shi, H.: Keys to better image inpainting: structure and texture go hand in hand. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 208\u2013217 (2023)","DOI":"10.1109\/WACV56688.2023.00029"},{"key":"11_CR17","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: International Conference on Learning Representations (2018)"},{"key":"11_CR18","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. arXiv preprint arXiv:2206.00364 (2022)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"11_CR21","unstructured":"Kim, D., Shin, S., Song, K., Kang, W., Moon, I.C.: Soft truncation: a universal training technique of score-based diffusion model for high precision score estimation. In: International Conference on Machine Learning, pp. 11201\u201311228. PMLR (2022)"},{"key":"11_CR22","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"11_CR23","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky, A.: Learning Multiple Layers of Features from Tiny Images. University of Toronto, Tech. rep. (2009)"},{"key":"11_CR24","unstructured":"Li, S., et al.: Entropy-driven sampling and training scheme for conditional diffusion generation. arXiv preprint arXiv:2206.11474 (2022)"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Li, W., Lin, Z., Zhou, K., Qi, L., Wang, Y., Jia, J.: MAT: mask-aware transformer for large hole image inpainting. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10758\u201310768 (2022)","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Q-diffusion: quantizing diffusion models. In: IEEE\/CVF International Conference on Computer Vision, pp. 17535\u201317545 (2023)","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"11_CR27","unstructured":"Liu, L., Ren, Y., Lin, Z., Zhao, Z.: Pseudo numerical methods for diffusion models on manifolds. arXiv preprint arXiv:2202.09778 (2022)"},{"key":"11_CR28","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: IEEE International Conference on Computer Vision, pp. 3730\u20133738 (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"11_CR30","first-page":"5775","volume":"35","author":"C Lu","year":"2022","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-Solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. Adv. Neural. Inf. Process. Syst. 35, 5775\u20135787 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Lu, Z., Jiang, J., Huang, J., Wu, G., Liu, X.: GLaMa: joint spatial and frequency loss for general image inpainting. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1301\u20131310 (2022)","DOI":"10.1109\/CVPRW56347.2022.00136"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: RePaint: inpainting using denoising diffusion probabilistic models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Moghadam, P.A., et al.: A morphology focused diffusion probabilistic model for synthesis of histopathology images. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2000\u20132009 (2023)","DOI":"10.1109\/WACV56688.2023.00204"},{"key":"11_CR34","unstructured":"Nash, C., Menick, J., Dieleman, S., Battaglia, P.W.: Generating images with sparse representations. arXiv preprint arXiv:2103.03841 (2021)"},{"key":"11_CR35","unstructured":"Pandey, K., Mukherjee, A., Rai, P., Kumar, A.: DiffuseVAE: Efficient, controllable and high-fidelity generation from low-dimensional latents. arXiv preprint arXiv:2201.00308 (2022)"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10619\u201310629 (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"11_CR37","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Schonfeld, E., Schiele, B., Khoreva, A.: A U-net based discriminator for generative adversarial networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8207\u20138216 (2020)","DOI":"10.1109\/CVPR42600.2020.00823"},{"key":"11_CR40","first-page":"12533","volume":"34","author":"A Sinha","year":"2021","unstructured":"Sinha, A., Song, J., Meng, C., Ermon, S.: D2C: diffusion-decoding models for few-shot conditional generation. Adv. Neural. Inf. Process. Syst. 34, 12533\u201312548 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR41","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265 (2015)"},{"key":"11_CR42","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021)"},{"key":"11_CR43","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"11_CR44","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"11_CR45","unstructured":"Such, F.P., Rawal, A., Lehman, J., Stanley, K., Clune, J.: Generative teaching networks: accelerating neural architecture search by learning to generate synthetic training data. In: International Conference on Machine Learning, pp. 9206\u20139216 (2020)"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Suvorov, R., et al.: Resolution-robust large mask inpainting with Fourier convolutions. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2149\u20132159 (2022)","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"11_CR47","first-page":"19667","volume":"33","author":"A Vahdat","year":"2020","unstructured":"Vahdat, A., Kautz, J.: NVAE: a deep hierarchical variational autoencoder. Adv. Neural. Inf. Process. Syst. 33, 19667\u201319679 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR48","first-page":"11287","volume":"34","author":"A Vahdat","year":"2021","unstructured":"Vahdat, A., Kreis, K., Kautz, J.: Score-based generative modeling in latent space. Adv. Neural. Inf. Process. Syst. 34, 11287\u201311302 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR49","unstructured":"Wang, Z., et al.: Patch diffusion: Faster and more data-efficient training of diffusion models. arXiv preprint arXiv:2304.12526 (2023)"},{"key":"11_CR50","unstructured":"Wang, Z., Zheng, H., He, P., Chen, W., Zhou, M.: Diffusion-GAN: training GANs with diffusion. In: International Conference on Learning Representations (2023)"},{"issue":"4","key":"11_CR51","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"11_CR52","unstructured":"Xiao, Z., Kreis, K., Vahdat, A.: Tackling the generative learning trilemma with denoising diffusion GANs. arXiv preprint arXiv:2112.07804 (2021)"},{"key":"11_CR53","unstructured":"Xu, Y., Liu, Z., Tian, Y., Tong, S., Tegmark, M., Jaakkola, T.: PFGM++: Unlocking the potential of physics-inspired generative models. arXiv preprint arXiv:2302.04265 (2023)"},{"key":"11_CR54","unstructured":"Xu, Y., Tong, S., Jaakkola, T.S.: Stable target field for reduced variance score estimation in diffusion models. In: International Conference on Learning Representations (2023)"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Yin, X., Huang, D., Fu, Z., Wang, Y., Chen, L.: Segmentation-reconstruction-guided facial image de-occlusion. In: IEEE International Conference on Automatic Face and Gesture Recognition (FG), pp.\u00a01\u20138 (2023)","DOI":"10.1109\/FG57933.2023.10042570"},{"key":"11_CR56","doi-asserted-by":"crossref","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5505\u20135514 (2018)","DOI":"10.1109\/CVPR.2018.00577"},{"key":"11_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, N., Liu, N., Han, J., Wan, K., Shao, L.: Face de-occlusion with deep cascade guidance learning. IEEE Trans. Multimedia 25, 3217\u20133229 (2022)","DOI":"10.1109\/TMM.2022.3157036"},{"key":"11_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"11_CR59","unstructured":"Zhao, S., et al.: Large scale image completion via co-modulated generative adversarial networks. arXiv preprint arXiv:2103.10428 (2021)"},{"key":"11_CR60","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"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\/978-3-031-73030-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T17:13:47Z","timestamp":1732554827000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73030-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031730290","9783031730306"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73030-6_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 November 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"}}]}}