# GRACE: Geometry- and Ray-Aware Camera-Efficient Multi-View Pedestrian Tracking

arXiv: https://arxiv.org/abs/2609.16872 · HTML: https://mlsanity.com/paper/2609.16872/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [Multiview Detection with Feature Perspective Transformation](https://mlsanity.com/paper/2007.07247/) (2020)
- [CAPE: Camera View Position Embedding for Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.10209/) (2023)
- [EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View](https://mlsanity.com/paper/2310.13350/) (2023)
- [Lifting Multi-View Detection and Tracking to the Bird's Eye View](https://mlsanity.com/paper/2403.12573/) (2024)
- [Viewpoint Equivariance for Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.14548/) (2023)
- [Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker](https://mlsanity.com/paper/2205.00968/) (2022)
- [RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategies](https://mlsanity.com/paper/2407.14923/) (2024)

## Abstract (arXiv)

Reducing the number of cameras reduces the deployment cost but removes views that correct BEV responses stretched away from true pedestrian positions by projection and short score drops that can split tracks} in Bird's-Eye View (BEV) tracking. We introduce GRACE, a camera-efficient multi-view tracker with three components. Volumetric-Guided Fusion combines homography-based BEV features with features lifted through 3D space. Ray Conditioning exposes each camera's viewing direction to the fusion network. Its tracking component, BEV Track Recovery (BTR), uses low-confidence detections only to continue existing tracks. The same detections cannot start new tracks. With two WildTrack cameras, GRACE improves MOTA from 83.54 for TrackTacular, our baseline, to 91.07.