{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:29:28Z","timestamp":1762342168047,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1913602"],"award-info":[{"award-number":["U1913602"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611807","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"2865-2876","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Diffusion-Augmented Depth Prediction with Sparse Annotations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7799-3407","authenticated-orcid":false,"given":"Jiaqi","family":"Li","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2785-9638","authenticated-orcid":false,"given":"Yiran","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8804-191X","authenticated-orcid":false,"given":"Zihao","family":"Huang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7996-8927","authenticated-orcid":false,"given":"Jinghong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0884-5126","authenticated-orcid":false,"given":"Ke","family":"Xian","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9223-1863","authenticated-orcid":false,"given":"Zhiguo","family":"Cao","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9954-6294","authenticated-orcid":false,"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Inc., San Jose, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Segdiff: Image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390","author":"Amit Tomer","year":"2021","unstructured":"Tomer Amit, Eliya Nachmani, Tal Shaharbany, and Lior Wolf. 2021. Segdiff: Image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390 (2021)."},{"key":"e_1_3_2_1_2_1","unstructured":"Fan Bao Chongxuan Li Jun Zhu and Bo Zhang. 2022. Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models. (2022)."},{"key":"e_1_3_2_1_3_1","volume-title":"Label-Efficient Semantic Segmentation with Diffusion Models. In International Conference on Learning Representations.","author":"Baranchuk Dmitry","year":"2022","unstructured":"Dmitry Baranchuk, Ivan Rubachev, Andrey Voynov, Valentin Khrulkov, and Artem Babenko. 2022. Label-Efficient Semantic Segmentation with Diffusion Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"e_1_3_2_1_5_1","unstructured":"Andrew Brock Jeff Donahue and Karen Simonyan. 2019. Large scale GAN training for high fidelity natural image synthesis. (2019)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_8_1","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems, Vol. 34 (2021), 8780--8794.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"volume-title":"Advances in neural information processing systems","author":"Eigen David","key":"e_1_3_2_1_10_1","unstructured":"David Eigen, Christian Puhrsch, and Rob Fergus. 2014. Depth map prediction from a single image using a multi-scale deep network. In Advances in neural information processing systems, Vol. 27. 2366--2374."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 3828--3838","author":"Godard C.","key":"e_1_3_2_1_14_1","unstructured":"C. Godard, O. Aodha, M. Firman, and G. Brostow. 2019. Digging into self-supervised monocular depth estimation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 3828--3838."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01093"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150884"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196781"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_23_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, Vol. 33 (2020), 6840--6851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_25_1","unstructured":"Jonathan Ho Tim Salimans Alexey A Gritsenko William Chan Mohammad Norouzi and David J Fleet. [n. d.]. Video Diffusion Models. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_26_1","volume-title":"Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries. In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). 1043--1051","author":"Hu Junjie","year":"2019","unstructured":"Junjie Hu, Mete Ozay, Yan Zhang, and Takayuki Okatani. 2019. Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries. In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). 1043--1051."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00288"},{"key":"e_1_3_2_1_28_1","volume-title":"European Conference on Computer Vision. Springer, 71--91","author":"Ignatov Andrey","year":"2022","unstructured":"Andrey Ignatov, Grigory Malivenko, Radu Timofte, Lukasz Treszczotko, Xin Chang, Piotr Ksiazek, Michal Lopuszynski, Maciej Pioro, Rafal Rudnicki, Maciej Smyl, et al. 2022. Efficient single-image depth estimation on mobile devices, mobile AI & AIM 2022 challenge: report. In European Conference on Computer Vision. Springer, 71--91."},{"key":"e_1_3_2_1_29_1","volume-title":"Dong Wook Ko, and Il Hong Suh","author":"Lee Jin Han","year":"2019","unstructured":"Jin Han Lee, Myung-Kyu Han, Dong Wook Ko, and Il Hong Suh. 2019. From big to small: Multi-scale local planar guidance for monocular depth estimation. arXiv preprint arXiv:1907.10326 (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_32_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 8912--8921","author":"Lyu Zhaoyang","year":"2021","unstructured":"Zhaoyang Lyu, Zhifeng Kong, Xudong Xu, Liang Pan, and Dahua Lin. 2021. Differentiable Diffusion for Dense Depth Estimation From Multi-View Images. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 8912--8921."},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Machine Learning. PMLR, 8162--8171","author":"Nichol Alexander Quinn","year":"2021","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International Conference on Machine Learning. PMLR, 8162--8171."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"e_1_3_2_1_36_1","volume-title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer","author":"Ranftl Ren\u00e9","year":"2020","unstructured":"Ren\u00e9 Ranftl, Katrin Lasinger, David Hafner, Konrad Schindler, and Vladlen Koltun. 2020. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 03 (2020), 1623--1637."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"e_1_3_2_1_39_1","volume-title":"Progressive Distillation for Fast Sampling of Diffusion Models. In International Conference on Learning Representations.","author":"Salimans Tim","year":"2022","unstructured":"Tim Salimans and Jonathan Ho. 2022. Progressive Distillation for Fast Sampling of Diffusion Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_40_1","volume-title":"Structure-from-Motion Revisited. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4104--4113","author":"Sch\u00f6nberger Johannes Lutz","year":"2016","unstructured":"Johannes Lutz Sch\u00f6nberger and Jan-Michael Frahm. 2016. Structure-from-Motion Revisited. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4104--4113."},{"key":"e_1_3_2_1_41_1","volume-title":"Feature-Metric Loss for Self-Supervised Learning of Depth and Egomotion. In European Conference on Computer Vision (ECCV). Springer, 572--588","author":"Shu Chang","year":"2020","unstructured":"Chang Shu, Kun Yu, Zhixiang Duan, and Kuiyuan Yang. 2020. Feature-Metric Loss for Self-Supervised Learning of Depth and Egomotion. In European Conference on Computer Vision (ECCV). Springer, 572--588."},{"key":"e_1_3_2_1_42_1","volume-title":"International Conference on Machine Learning. PMLR, 2256--2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning. PMLR, 2256--2265."},{"key":"e_1_3_2_1_43_1","volume-title":"Denoising Diffusion Implicit Models. In International Conference on Learning Representations.","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020a. Denoising Diffusion Implicit Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_44_1","unstructured":"Yang Song Jascha Sohl-Dickstein Diederik P Kingma Abhishek Kumar Stefano Ermon and Ben Poole. 2020b. Score-based generative modeling through stochastic differential equations. (2020)."},{"volume-title":"Advances in neural information processing systems","author":"Vaswani Ashish","key":"e_1_3_2_1_45_1","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems, Vol. 30."},{"key":"e_1_3_2_1_46_1","volume-title":"PlaneDepth: Plane-Based Self-Supervised Monocular Depth Estimation. arXiv preprint arXiv:2210.01612","author":"Wang Ruoyu","year":"2022","unstructured":"Ruoyu Wang, Zehao Yu, and Shenghua Gao. 2022b. PlaneDepth: Plane-Based Self-Supervised Monocular Depth Estimation. arXiv preprint arXiv:2210.01612 (2022)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00278"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547978"},{"key":"e_1_3_2_1_49_1","volume-title":"Neural Video Depth Stabilizer. arXiv preprint arXiv:2307.08695","author":"Wang Yiran","year":"2023","unstructured":"Yiran Wang, Min Shi, Jiaqi Li, Zihao Huang, Zhiguo Cao, Jianming Zhang, Ke Xian, and Guosheng Lin. 2023. Neural Video Depth Stabilizer. arXiv preprint arXiv:2307.08695 (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of The 6th Conference on Robot Learning","volume":"205","author":"Wei Yi","year":"2023","unstructured":"Yi Wei, Linqing Zhao, Wenzhao Zheng, Zheng Zhu, Yongming Rao, Guan Huang, Jiwen Lu, and Jie Zhou. 2023. SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation. In Proceedings of The 6th Conference on Robot Learning, Vol. 205. 539--549."},{"key":"e_1_3_2_1_52_1","volume-title":"International Conference on Medical Imaging with Deep Learning. PMLR, 1336--1348","author":"Wolleb Julia","year":"2022","unstructured":"Julia Wolleb, Robin Sandk\u00fchler, Florentin Bieder, Philippe Valmaggia, and Philippe C Cattin. 2022. Diffusion models for implicit image segmentation ensembles. In International Conference on Medical Imaging with Deep Learning. PMLR, 1336--1348."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548394"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 3916--3925","author":"Yuan Weihao","year":"2022","unstructured":"Weihao Yuan, Xiaodong Gu, Zuozhuo Dai, Siyu Zhu, and Ping Tan. 2022. NeWCRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 3916--3925."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611807","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611807","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:10:33Z","timestamp":1755821433000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611807"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":57,"alternative-id":["10.1145\/3581783.3611807","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611807","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}