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

• URL: http://arxiv.org/abs/2512.02006v1
• Date: Mon, 01 Dec 2025 18:59:01 GMT
• Title: MV-TAP: Tracking Any Point in Multi-View Videos
• Abstract summary: MV-TAP is a novel point tracker that tracks points across multi-view videos of dynamic scenes by leveraging cross-view information.<n>To support this task, we construct a large-scale synthetic training dataset and real-world evaluation sets tailored for multi-view tracking.
• Score: 34.91357343992975
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views [50.26507994908593]
  We introduce TAPVid-MV (Tracking Any Point in Video across Multiple Views), the first benchmark for this setting.<n>It contains a curated set of 284 sequences, 1,142 calibrated camera streams, and 109,769 point tracks across seven subsets spanning indoor and outdoor domains.<n>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.
  arXiv  Detail & Related papers  (2026-09-01T21:58:51Z)
• Beyond Appearance: A Multi-cue Framework and Large-scale Benchmark for Pedestrian Association and Tracking on Mobile Aerial-Ground Platforms [20.14740379542179]
  We propose a viewpoint-robust Feature Unification framework for multi-view aSsociation and IdentificatiON.<n>We also introduce RealMvMoAT, a large-scale benchmark featuring substantial inter- and intra-camera viewpoint variation.
  arXiv  Detail & Related papers  (2026-07-26T19:06:04Z)
• MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs [40.317798580235]
  Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model.<n>We introduce MultiView-Bench, a diagnostic benchmark expressly designed to evaluate multi-view integration for holistic 3D scene comprehension.<n>We propose ViewNavigator, a multi-agent framework that actively selects informative viewpoints, perceives, and fuses multi-view evidence, improving diverse base models on MultiView-Bench even under a strict budget-matched comparison.
  arXiv  Detail & Related papers  (2026-07-09T22:22:42Z)
• MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation [50.65653874052261]
  We introduce MVTrack4Gen, a motion-aware training framework for camera-conditioning-only novel-view video diffusion models.<n>Our key finding is that specific attention layers encode strong correspondence cues, where query features attend to key features at geometrically corresponding locations.<n>By explicitly strengthening these motion-aware correspondences, MVTrack4Gen improves existing models to better follow the motion in the reference view and maintain cross-view geometric consistency.
  arXiv  Detail & Related papers  (2026-06-24T17:56:33Z)
• Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes [48.537990488697965]
  Multi-view crowd tracking estimates each person's tracking trajectories on the ground of the scene.<n>Recent research works mainly rely on CNNs-based multi-view crowd tracking architectures.<n>We propose a Transformer-based multi-view crowd tracking model, textitMVTrackTrans, which adopts interactions between camera views and the ground plane for enhanced multi-view tracking performance.
  arXiv  Detail & Related papers  (2026-04-21T10:26:23Z)
• A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects [53.15503034595476]
  Video Scene Parsing (VSP) has emerged as a cornerstone in computer vision.<n>VSP has emerged as a cornerstone in computer vision, facilitating the simultaneous segmentation, recognition, and tracking of diverse visual entities in dynamic scenes.
  arXiv  Detail & Related papers  (2025-06-16T14:39:03Z)
• FusionTrack: End-to-End Multi-Object Tracking in Arbitrary Multi-View Environment [7.5152380894919055]
  We propose an end-to-end framework that reasonably integrates tracking and re-identification to leverage multi-view information for robust trajectory association.<n>Experiments on our MDMOT and other benchmark datasets demonstrate that FusionTrack achieves state-of-the-art performance in both single-view and multi-view tracking.
  arXiv  Detail & Related papers  (2025-05-24T14:51:19Z)
• NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models [11.184459657989914]
  We introduce NuPlanQA-Eval, a multi-view, multi-modal evaluation benchmark for driving scene understanding.<n>We also propose NuPlanQA-1M, a large-scale dataset comprising 1M real-world visual question-answering (VQA) pairs.<n>Our evaluation results reveal key challenges that existing MLLMs face in driving scene-specific perception and spatial reasoning from ego-centric perspectives.
  arXiv  Detail & Related papers  (2025-03-17T03:12:39Z)
• Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention [61.3281618482513]
  We present CogDriving, a novel network designed for synthesizing high-quality multi-view driving videos.<n>CogDriving leverages a Diffusion Transformer architecture with holistic-4D attention modules, enabling simultaneous associations across the dimensions.<n>CogDriving demonstrates strong performance on the nuScenes validation set, achieving an FVD score of 37.8, highlighting its ability to generate realistic driving videos.
  arXiv  Detail & Related papers  (2024-12-04T18:02:49Z)
• MCTR: Multi Camera Tracking Transformer [45.66952089591361]
  Multi-Camera Tracking tRansformer (MCTR) is a novel end-to-end approach tailored for multi-object detection and tracking across multiple cameras. MCTR leverages end-to-end detectors like DEtector TRansformer (DETR) to produce detections and detection embeddings independently for each camera view. The framework maintains set of track embeddings that encaplusate global information about the tracked objects, and updates them at every frame by integrating local information from the view-specific detection embeddings.
  arXiv  Detail & Related papers  (2024-08-23T17:37:03Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.<n>Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations.<n>We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers [9.271932084757646]
  3D occupancy represents the entire scene without distinguishing between foreground and background by the physical space into a grid map. We propose our learning-first view attention mechanism for effective multi-view feature aggregation. We present FlowOcc3D, a benchmark built on top existing high-quality datasets.
  arXiv  Detail & Related papers  (2024-05-07T13:15:07Z)
• MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark [63.878793340338035]
  Multi-target multi-camera tracking is a crucial task that involves identifying and tracking individuals over time using video streams from multiple cameras. Existing datasets for this task are either synthetically generated or artificially constructed within a controlled camera network setting. We present MTMMC, a real-world, large-scale dataset that includes long video sequences captured by 16 multi-modal cameras in two different environments.
  arXiv  Detail & Related papers  (2024-03-29T15:08:37Z)
• CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation [31.167405688707575]
  We propose a framework for instance-level visual analysis on video frames. It can simultaneously conduct object detection, instance segmentation, and multi-object tracking. We evaluate the proposed method extensively on KITTI MOTS and MOTS Challenge datasets.
  arXiv  Detail & Related papers  (2023-11-02T04:32:24Z)
• Multi-Spectral Image Stitching via Spatial Graph Reasoning [52.27796682972484]
  We propose a spatial graph reasoning based multi-spectral image stitching method. We embed multi-scale complementary features from the same view position into a set of nodes. By introducing long-range coherence along spatial and channel dimensions, the complementarity of pixel relations and channel interdependencies aids in the reconstruction of aligned multi-view features.
  arXiv  Detail & Related papers  (2023-07-31T15:04:52Z)
• DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes [74.64897845999677]
  We introduce a new cross-view multi-object tracking dataset for DIVerse Open scenes with dense tracking pedestrians. Our DIVOTrack has fifteen distinct scenarios and 953 cross-view tracks, surpassing all cross-view multi-object tracking datasets currently available. Furthermore, we provide a novel baseline cross-view tracking method with a unified joint detection and cross-view tracking framework named CrossMOT.
  arXiv  Detail & Related papers  (2023-02-15T14:10:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.