AI RESEARCH
SAMOFT: Robust Multi-Object Tracking via Region and Flow
arXiv CS.CV
•
ArXi:2605.09417v1 Announce Type: new Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent identities across frames. However, most existing approaches primarily rely on instance-level object features for trajectory association, which often leads to degraded performance under challenging conditions such as object deformation, nonlinear motion, and occlusion. In this work, we propose SAMOFT, a robust tracker that leverages pixel-level cues to improve robustness under complex motion scenarios.