AI RESEARCH
Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification
arXiv CS.CV
•
ArXi:2406.16042v3 Announce Type: replace Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across images. Existing datasets frequently lack diversity and scalability in these aspects, hindering the generalization of Re-ID models to new camera systems or environments. To overcome this, we propose Pose-dIVE, a novel data augmentation approach that incorporates sparse and underrepresented human pose and camera viewpoint examples into the.