arXiv:2610.01314v1 Announce Type: new Abstract: Dynamic scenes may be captured by a moving camera, multiple video streams, or images taken at different times. These observations reveal complementary...
TrackEverything is a 3D point tracker that overcomes the trade‑off between sparse long‑horizon tracking and dense short‑clip tracking by representing videos as persistent 3D scene tracks in world coordinates. It introduces voxel‑based de‑duplication at sliding‑window boundaries, a two‑stage refinement process (endpoint refiner and lightweight trajectory refiner), and a 3D WAFT module that replaces memory‑heavy 4D correlation volumes with efficient feature sampling. The method can track all visible points in videos longer than 1000 frames using only 40 GB of GPU memory, outperforming existing dense trackers on short clips and matching sparse trackers on long sequences.
The paper introduces PLANET, a multi‑object tracker that transcends traditional image‑plane limitations by incorporating 3D scene geometry into its query formation. By lifting 2D tracking datasets into 3D and embedding reconstructed geometry into features and positional encodings, PLANET encourages queries to encode object positions. An auxiliary 3D location prediction task and a dual‑resolution temporal memory further enhance performance, enabling state‑of‑the‑art results on three diverse benchmarks.
Monocular videos record 3D scenes as sequences of 2D image-plane projections, obscuring depth and spatial relationships. Multi-object trackers localize and associate objects primarily using appearance...
TAPVid-MV is a new benchmark for tracking any point in 3D across multiple synchronized camera views. It comprises 284 sequences, 1,142 calibrated camera streams, and 109,769 point tracks, covering indoor and outdoor domains and derived from various modalities such as depth, LiDAR, SLAM, and simulation. The dataset is visually verified, and evaluation shows that current multi‑view trackers do not consistently outperform monocular trackers, highlighting geometry recovery as a key bottleneck.
OmniGlimpse introduces an asymmetric propose‑verify framework for online multi‑view tracking, separating short‑term adaptive association from long‑term stable identity consolidation. It maps short‑term local and cross‑view evidence into target‑specific adaptive spaces for proposing associations, while maintaining long‑term identity distributions in a canonical space defined by a frozen encoder for verification. The method achieves significant gains over the best online baseline on M3Track and MvMHAT, outperforming offline‑trained references in IDF1 without any offline scene‑specific training.
End-to-end multi-object trackers have narrowed the gap with classical tracking-by-detection on association-difficult benchmarks. Yet they still make spatially implausible errors no classical tracker w...
arXiv:2610.10391v1 Announce Type: new Abstract: End-to-end multi-object trackers have narrowed the gap with classical tracking-by-detection on association-difficult benchmarks. Yet they still make sp...
arXiv:2607. 17157v1 Announce Type: cross Abstract: Multi-object tracking (MOT) aims to localize multiple objects in videos while preserving their identities over time.
Physical AI Smart Spaces is the first benchmark that offers large‑scale, multi‑class, multi‑camera 3D perception data for indoor smart spaces. It includes over 280 hours of synchronized 1080p footage from nearly 1,800 cameras in warehouses, hospitals, and retail venues, with automatic annotations for identities, 2D and 3D bounding boxes, camera calibration, and depth. The benchmark spans synthetic generation, appearance augmentation, and real‑world Sim2Real evaluation, and introduces a 3D version of Higher Order Tracking Accuracy (HOTA) for evaluating multi‑class 3D box tracking.
Syn2RealTrack addresses the synthetic‑to‑real gap in multi‑camera 3D perception for warehouses by decomposing it into three distinct issues: camera calibration, object shape prior, and known object census. The pipeline corrects lens distortion from images, fuses detections with a visibility‑weighted part‑based descriptor, measures person height directly from calibration, and uses a closed‑world cardinality prior with a causal filter to eliminate phantom boxes. These local remedies allow the system to adapt without retraining a feature extractor, achieving a 3D HOTA of 52.0118% on the AI City Challenge 2026 Track 1.
arXiv:2608. 16480v1 Announce Type: cross Abstract: We present RISE (Roadside Infrastructure Sequence Understanding and Evaluation), a framework spanning metric 3D tracking and structured vision-language reasoning in roadside sequences.