Metraipolis › archive › dc_0d8d69736ff6
TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views — arXiv:2609.01899
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01899
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:49:47.072Z
- SHA-256 of the archived text
6cf2dad250332101d3802cd0e3faec65f542d9c9872a630562d6d4a2ddb7e642- Stable URL of this page
https://metraipolis.com/documento/dc_0d8d69736ff6
How to cite
TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views — arXiv:2609.01899 — arXiv (en), https://arxiv.org/abs/2609.01899 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d8d69736ff6 (Metraipolis archive dc_0d8d69736ff6, sha256 6cf2dad250332101d3802cd0e3faec65f542d9c9872a630562d6d4a2ddb7e642)
BibTeX
@misc{dc0d8d69736ff6,
title = {TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views — arXiv:2609.01899},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01899},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d8d69736ff6; sha256 6cf2dad250332101d3802cd0e3faec65f542d9c9872a630562d6d4a2ddb7e642},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01899. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-camera systems are increasingly practical for robotics, AR/VR, and autonomous driving because complementary views reduce depth ambiguity and preserve visibility under occlusion. Existing point-tracking benchmarks, however, focus on a single video or static multi-camera rigs. None test long-term 3D point tracking across several synchronized views under camera motion. We introduce TAPVid-MV (Tracking Any Point in Video across Multiple Views), the first benchmark for this setting. It contains a curated set of 238 sequences, 1,004 calibrated camera streams, and 74,147 point tracks across seven subsets spanning indoor and outdoor domains, from robotics and human activity to driving and synthetic procedural scenes. We obtain these trajectories using dataset-specific auxiliary modalities: sensor depth, LiDAR, SLAM and SfM points, human meshes, posed object meshes, and simulation. Every sequence and trajectory is visually verified by human annotators. Across more than 30 baselines, no method comes close to solving the task. Surprisingly, existing multi-view point trackers do not consistently outperform monocular point trackers. By evaluating reconstruction and point tracking on the same datasets, TAPVid-MV helps distinguish errors in recovered geometry from errors in point correspondence. Through this joint analysis, we identify geometry recovery as a major bottleneck for accurate 3D point tracking. Beyond multi-view 3D point tracking, our released annotations support monocular 2D and 3D point tracking, future-trajectory prediction, and 4D reconstruction. Project page: this https URL Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.01899 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T05:25:58.041Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).