DPoser: Diffusion Model as Robust 3D Human Pose Prior

arXiv:2312.05541v2 Announce Type: replace
Abstract: This work targets to construct a robust human pose prior. However, it remains a persistent challenge due to biomechanical constraints and diverse human movements. Traditional priors like VAEs and NDFs often exhibit shortcomings in realism and generalization, notably with unseen noisy poses. To address these issues, we introduce DPoser, a robust and versatile human pose prior built upon diffusion models. DPoser regards various pose-centric tasks as inverse problems and employs variational diffusion sampling for efficient …

abstract arxiv challenge constraints construct cs.cv diffusion diffusion model diverse however human movements prior robust targets type work