mlsanityData to 14 Oct 2026

MV-TAP: Tracking Any Point in Multi-View Videos

arXiv 2512.02006 ↗First posted 1 Dec 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Multi-view camera systems enable rich observations of complex real-world scenes, and understanding dynamic objects in multi-view settings has become central to various applications. In this work, we present MV-TAP, a novel point tracker that tracks points across multi-view videos of dynamic scenes by leveraging cross-view information. MV-TAP utilizes camera geometry and a cross-view attention mechanism to aggregate spatio-temporal information across views, enabling more complete and reliable trajectory estimation in multi-view videos. To support this task, we construct a large-scale synthetic training dataset and real-world evaluation sets tailored for multi-view tracking. Extensive experiments demonstrate that MV-TAP outperforms existing point-tracking methods on challenging benchmarks, establishing an effective baseline for advancing research in multi-view point tracking.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 38 of its 49 references that are in the map. First posted on arXiv 1 Dec 2025.

Builds on

38 of 49 references.

References · 38

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  2. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  4. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  5. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  6. 2025DINOv3cited by 1,414
  7. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  8. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  9. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  10. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  11. 2023CoTracker: It is Better to Track Togethercited by 522
  12. 2022Kubric: A scalable dataset generatorcited by 381
26 more
  1. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 325
  2. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  3. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 301
  4. 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 287
  5. 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 263
  6. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
  7. 2022Particle Video Revisited: Tracking Through Occlusions Using Point Trajectoriescited by 217
  8. 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 181
  9. 2024Motion Prompting: Controlling Video Generation with Motion Trajectoriescited by 178
  10. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 174
  11. 2024Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulationcited by 124
  12. 2023RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitationcited by 90
  13. 2025St4RTrack: Simultaneous 4D Reconstruction and Tracking in the Worldcited by 89
  14. 2023Multi-View Masked World Models for Visual Robotic Manipulationcited by 80
  15. 2024Local All-Pair Correspondence for Point Trackingcited by 80
  16. 2024TAPVid-3D: A Benchmark for Tracking Any Point in 3Dcited by 72
  17. 2025TAPIP3D: Tracking Any Point in Persistent 3D Geometrycited by 69
  18. 2025AllTracker: Efficient Dense Point Tracking at High Resolutioncited by 58
  19. 2024Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generationcited by 44
  20. 2025TAPNext: Tracking Any Point (TAP) as Next Token Predictioncited by 37
  21. 2024Harmony4D: A Video Dataset for In-The-Wild Close Human Interactionscited by 31
  22. 2021HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Mediacited by 29
  23. 2023DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videoscited by 25
  24. 2025Multi-View 3D Point Trackingcited by 17
  25. 2025NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Drivingcited by 12
  26. 2025AnthroTAP: Learning Point Tracking with Real-World Motioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstructioncited by 2
  2. 2026MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generationcited by 2
  3. 2026TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Viewscited by 1
  4. 2026ARROW: Arbitrary Reconstruction and Tracking of 4D Observations in the Wildcited by 0