PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery

arXiv:2403.12473v1 Announce Type: new
Abstract: With the recent advancements in single-image-based human mesh recovery, there is a growing interest in enhancing its performance in certain extreme scenarios, such as occlusion, while maintaining overall model accuracy. Although obtaining accurately annotated 3D human poses under occlusion is challenging, there is still a wealth of rich and precise 2D pose annotations that can be leveraged. However, existing works mostly focus on directly leveraging 2D pose coordinates to estimate 3D pose and mesh. In …

abstract accuracy arxiv cs.cv human image mesh model accuracy performance recovery robust token transformer type