# Look Around and Pay Attention: Multi-camera Point Tracking Reimagined with Transformers

arXiv: https://arxiv.org/abs/2512.04213 · HTML: https://mlsanity.com/paper/2512.04213/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 3 Dec 2025.

## Builds on (most cited first, 18 of 18)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking](https://mlsanity.com/paper/2307.15055/) (2023)
- [SpatialTracker: Tracking Any 2D Pixels in 3D Space](https://mlsanity.com/paper/2404.04319/) (2024)
- [MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds](https://mlsanity.com/paper/2405.17421/) (2024)
- [BootsTAP: Bootstrapped Training for Tracking-Any-Point](https://mlsanity.com/paper/2402.00847/) (2024)
- [Epipolar Transformers](https://mlsanity.com/paper/2005.04551/) (2020)
- [SpatialTrackerV2: 3D Point Tracking Made Easy](https://mlsanity.com/paper/2507.12462/) (2025)
- [TAPVid-3D: A Benchmark for Tracking Any Point in 3D](https://mlsanity.com/paper/2407.05921/) (2024)
- [TAPIP3D: Tracking Any Point in Persistent 3D Geometry](https://mlsanity.com/paper/2504.14717/) (2025)
- [DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video](https://mlsanity.com/paper/2403.14548/) (2024)
- [MVSTER: Epipolar Transformer for Efficient Multi-View Stereo](https://mlsanity.com/paper/2204.07346/) (2022)
- [Robo-GS: A Physics Consistent Spatial-Temporal Model for Robotic Arm with Hybrid Representation](https://mlsanity.com/paper/2408.14873/) (2024)
- [Pre-training Auto-regressive Robotic Models with 4D Representations](https://mlsanity.com/paper/2502.13142/) (2025)
- [Track-On: Transformer-based Online Point Tracking with Memory](https://mlsanity.com/paper/2501.18487/) (2025)
- [Fast Encoder-Based 3D from Casual Videos via Point Track Processing](https://mlsanity.com/paper/2404.07097/) (2024)
- [MCTR: Multi Camera Tracking Transformer](https://mlsanity.com/paper/2408.13243/) (2024)
- [No Train Yet Gain: Towards Generic Multi-Object Tracking in Sports and Beyond](https://mlsanity.com/paper/2506.01373/) (2025)

## Built on by (most cited first, 4 of 4)

- [TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views](https://mlsanity.com/paper/2609.01899/) (2026)
- [K-Track: Kalman-Enhanced Tracking for Accelerating Deep Point Trackers on Edge Devices](https://mlsanity.com/paper/2512.10628/) (2025)
- [UniTrack: Differentiable Graph Representation Learning for Multi-Object Tracking](https://mlsanity.com/paper/2602.05037/) (2026)
- [ARROW: Arbitrary Reconstruction and Tracking of 4D Observations in the Wild](https://mlsanity.com/paper/2610.01314/) (2026)

## Abstract (arXiv)

This paper presents LAPA (Look Around and Pay Attention), a novel end-to-end transformer-based architecture for multi-camera point tracking that integrates appearance-based matching with geometric constraints. Traditional pipelines decouple detection, association, and tracking, leading to error propagation and temporal inconsistency in challenging scenarios. LAPA addresses these limitations by leveraging attention mechanisms to jointly reason across views and time, establishing soft correspondences through a cross-view attention mechanism enhanced with geometric priors. Instead of relying on classical triangulation, we construct 3D point representations via attention-weighted aggregation, inherently accommodating uncertainty and partial observations. Temporal consistency is further maintained through a transformer decoder that models long-range dependencies, preserving identities through extended occlusions. Extensive experiments on challenging datasets, including our newly created multi-camera (MC) versions of TAPVid-3D panoptic and PointOdyssey, demonstrate that our unified approach significantly outperforms existing methods, achieving 37.5% APD on TAPVid-3D-MC and 90.3% APD on PointOdyssey-MC, particularly excelling in scenarios with complex motions and occlusions. Code is available at https://github.com/ostadabbas/Look-Around-and-Pay-Attention-LAPA-