{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:50Z","timestamp":1779948110816,"version":"3.53.1"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00167","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1760-1770","source":"Crossref","is-referenced-by-count":0,"title":["Online Video Depth Anything: Temporally-Consistent Depth Prediction with Low Memory Consumption"],"prefix":"10.1109","author":[{"given":"Johann-Friedrich","family":"Feiden","sequence":"first","affiliation":[{"name":"Heidelberg University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"K\u00fcchler","sequence":"additional","affiliation":[{"name":"Heidelberg University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denis","family":"Zavadski","sequence":"additional","affiliation":[{"name":"Heidelberg University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bogdan","family":"Savchynskyy","sequence":"additional","affiliation":[{"name":"Heidelberg University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carsten","family":"Rother","sequence":"additional","affiliation":[{"name":"Heidelberg University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","article-title":"Depth pro: Sharp monocular metric depth in less than a second","volume-title":"International Conference on Learning Representations","author":"Bochkovskii"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref5","author":"Cabon","year":"2020","journal-title":"Virtual kitti 2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00899"},{"key":"ref8","article-title":"Transformers are ssms: generalized models and efficient algorithms through structured state space duality","volume-title":"Proceedings of the 41st International Conference on Machine Learning. JMLR.org","author":"Dao"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00514"},{"key":"ref10","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume":"27","author":"Eigen","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref13","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"First Conference on Language Modeling","author":"Gu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00193"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/s20082272"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00880"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00303"},{"key":"ref23","author":"Liang","year":"2024","journal-title":"Feedforward bullet-time reconstruction of dynamic scenes from monocular videos"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4443"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02125"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392377"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103441"},{"key":"ref29","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967590"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3017478"},{"key":"ref32","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv"},{"issue":"606\u2013624","key":"ref33","article-title":"Efficiently scaling transformer inference","volume-title":"Proceedings of machine learning and systems","volume":"5","author":"Pope"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02127"},{"key":"ref37","first-page":"16558","article-title":"Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras","volume":"34","author":"Teed","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","article-title":"Irs: A large synthetic indoor robotics stereo dataset for disparity and surface normal estimation","author":"Wang","journal-title":"ArXiv, abs\/1912.09678"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00868"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref45","article-title":"Depth any video with scalable synthetic data","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Yang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00136"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00804"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0917-8_2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00181"},{"key":"ref52","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459871"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01818"},{"key":"ref55","article-title":"Streaming 4d visual geometry transformer","author":"Zhuo","year":"2025","journal-title":"arXiv preprint"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533285.pdf?arnumber=11533285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:02:30Z","timestamp":1779944550000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00167","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}