Year: 2026
Type: preprint
Abstract: Outside-in multi-camera perception is increasingly important in indoor environments, where networks of static cameras must support multi-target tracking under occlusion and heterogeneous viewpoints. We evaluate Sparse4D, a query-based spatiotemporal 3D detection and tracking framework that fuses multi-view features in a shared world frame and propagates sparse object queries via instance memory. We study reduced input frame rates, post-training quantization (INT8 and FP8), transfer to the WILDTRACK benchmark, and Transformer Engine mixed-precision fine-tuning. To better capture identity stability, we report Average Track Duration (AvgTrackDur), which measures identity persistence in seconds. Sparse4D remains stable under moderate FPS reductions, but below 2 FPS, identity association collapses even when detections are stable. Selective quantization of the backbone and neck offers the best speed-accuracy trade-off, while attention-related modules are consistently sensitive to low precision. On WILDTRACK, low-FPS pretraining yields large zero-shot gains over the base checkpoint, while small-scale fine-tuning provides limited additional benefit. Transformer Engine mixed precision reduces latency and improves camera scalability, but can destabilize identity propagation, motivating stability-aware validation.
Source: arXiv (Cornell University)
Authors: Anderson, Ethan, Silva, Justin, Zheng, Kyle, Pusegaonkar, Sameer, Wang, Yizhou, Tang, Zheng, Biswas, Sujit
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7127427147
Cites:
Cited by:
Related to: