# ATLASFusion: Aggregation Tracking with Location-Aware Sparse Fusion for Robust Spatio-Temporal Multi-View Pedestrian Tracking

arXiv: https://arxiv.org/abs/2509.08421 · HTML: https://mlsanity.com/paper/2509.08421/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries](https://mlsanity.com/paper/2205.00613/) (2022)
- [Multiview Detection with Feature Perspective Transformation](https://mlsanity.com/paper/2007.07247/) (2020)
- [Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)](https://mlsanity.com/paper/2108.05888/) (2021)
- [Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection](https://mlsanity.com/paper/1704.05775/) (2017)
- [Deep Multi-camera People Detection](https://mlsanity.com/paper/1702.04593/) (2017)
- [EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View](https://mlsanity.com/paper/2310.13350/) (2023)
- [PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?](https://mlsanity.com/paper/2208.01957/) (2022)
- [Lifting Multi-View Detection and Tracking to the Bird's Eye View](https://mlsanity.com/paper/2403.12573/) (2024)
- [ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking](https://mlsanity.com/paper/2308.13229/) (2023)
- [Real-time 3D Deep Multi-Camera Tracking](https://mlsanity.com/paper/2003.11753/) (2020)
- [Multi-Target Multi-Camera Tracking of Vehicles using Metadata-Aided Re-ID and Trajectory-Based Camera Link Model](https://mlsanity.com/paper/2105.01213/) (2021)
- [MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos](https://mlsanity.com/paper/2412.00692/) (2024)
- [Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention](https://mlsanity.com/paper/2208.09211/) (2022)
- [MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost](https://mlsanity.com/paper/2509.01157/) (2025)

## Built on by (most cited first, 1 of 1)

- [ModTrack: Sensor-Agnostic Multi-View Tracking via Identity-Informed PHD Filtering with Covariance Propagation](https://mlsanity.com/paper/2603.15812/) (2026)

## Abstract (arXiv)

For multimedia spatial intelligence through time, multi-view multi-object tracking (MVMOT) suffers from persistent challenges in maintaining consistent object identities across different camera views, leading to tracking inaccuracies. A key source of these errors in modern methods is the distortion of feature representations when projecting from multiple views into a unified Bird's-Eye-View (BEV) space. This projection often creates non-uniform feature densities, harming the reliability of the fused representation. To address this, we present ATLASFusion, a reliability-aware sparse BEV fusion framework built on three complementary techniques: a sparse perspective transform that projects only valid feature points to prevent interpolation artifacts, density-aware weighted aggregation that assigns higher confidence to spatially reliable regions, and per-view BEV supervision that supervises each camera's BEV features independently before fusion. Experiments on the WildTrack and MultiViewX benchmarks demonstrated improvements in IDF1, MODP, and robustness over the baseline. ATLASFusion achieved a 95.9% IDF1 tracking score on WildTrack, the highest among the compared methods and improved the localization precision (MODP) from 75.0% to 89.2% on MultiViewX. ATLASFusion also exhibited strong robustness under calibration noise. When high-magnitude noise was injected, TrackTacular failed entirely at 0.0% MODA, whereas ATLASFusion retained 40.1% MODA. When the input resolution was reduced by half, MVTr failed entirely and TrackTacular degraded by 2.7% MODA, while ATLASFusion sustained 92.5% MODA with only a 1.1% decrease. These gains were achieved with negligible computational overhead.