{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:59Z","timestamp":1779948119353,"version":"3.53.1"},"reference-count":90,"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\/3dv69130.2026.00011","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"40-51","source":"Crossref","is-referenced-by-count":0,"title":["L4P: Towards Unified Low-Level 4D Vision Perception"],"prefix":"10.1109","author":[{"given":"Abhishek","family":"Badki","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Su","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Wen","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Orazio","family":"Gallo","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"V-JEPA 2: Self-supervised video models enable understanding, prediction and planning","author":"Assran","year":"2025","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"ref3","article-title":"ZoeDepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2413"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11024-6_55"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref7","article-title":"Virtual KITTI 2","author":"Cabon","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Segment and track anything","author":"Cheng","year":"2023","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00676"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0989"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"ref12","article-title":"BootsTAP: Boot-\\\\ strapped training for tracking-any-point","author":"Doersch","year":"2024","journal-title":"ArXiv Preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01804"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2605"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299035"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.161"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.106"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937611"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00298"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.228"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_42"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.381"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref32","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kolesnikov","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"ref34","article-title":"TAPVid-3D: A benchmark for tracking any point in 3d","author":"Koppula","year":"2024","journal-title":"ArXiv Preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00578"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00981"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392377"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00482"},{"key":"ref42","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01842"},{"key":"ref44","article-title":"Analytisch-Geometrische Entwicklungen","author":"Pl\u00fccker","year":"2025","journal-title":"GD Baedeker"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00225"},{"key":"ref48","article-title":"The surprising effectiveness of diffusion models for optical flow and monocular depth estimation","volume":"36","author":"Saxena","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_1"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02127"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01146"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141964"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref58","article-title":"Deepv2d: Video to depth with differentiable structure from motion","author":"Teed","year":"2018","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref60","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":"neurips"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.64"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.480"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00013"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32847"},{"key":"ref72","article-title":"TartanVO: A generalizable learning-based vo","volume-title":"Conference on Robot Learning (CoRL)","author":"Wang","year":"2020"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00868"},{"key":"ref75","article-title":"Internvideo2: Scaling video foundation models for multimodal video understanding","author":"Wang","year":"2024","journal-title":"ArXiv Preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01647"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.044"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.092"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00633"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"ref82","article-title":"Flow as the cross-domain manipulation interface","author":"Xu","year":"2024","journal-title":"corl"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00132"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref85","article-title":"Depth Anything V2","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"ref87","article-title":"Tapip3d: Tracking any point in persistent 3d geometry","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref88","article-title":"MonST3R: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"ArXiv Preprint"},{"key":"ref89","article-title":"Cameras as rays: Pose estimation via ray diffusion","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhang","year":"2024"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01818"}],"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\/11533335.pdf?arnumber=11533335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:03:10Z","timestamp":1779944590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00011","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}