Article

DepTR-MOT: Depth-Informed Trajectory Refinement for Multi-Object Tracking

DepTR-MOT proposes a category-agnostic DETR-based detector that embeds instance-level depth awareness into the detector through instance-level soft depth label supervision and dense depth map distillation, and outputs instance depth at inference to improve multi-object tracking under occlusion and close-proximity interactions.

Part of the event: DepTR-MOT: Depth-Refined Multi-Object Tracking

This page provides a summary and source link only.