Human Pose-Constrained UV Map Estimation
This work addresses the issue of incoherent UV maps in computer vision for detailed human analysis, representing an incremental improvement over previous methods.
The paper tackles the problem of UV map estimation for human posture analysis by integrating 2D human pose constraints to enforce global coherence and anatomical plausibility, resulting in consistent improvements on the DensePose COCO benchmark with reduced invalid mappings.
UV map estimation is used in computer vision for detailed analysis of human posture or activity. Previous methods assign pixels to body model vertices by comparing pixel descriptors independently, without enforcing global coherence or plausibility in the UV map. We propose Pose-Constrained Continuous Surface Embeddings (PC-CSE), which integrates estimated 2D human pose into the pixel-to-vertex assignment process. The pose provides global anatomical constraints, ensuring that UV maps remain coherent while preserving local precision. Evaluation on DensePose COCO demonstrates consistent improvement, regardless of the chosen 2D human pose model. Whole-body poses offer better constraints by incorporating additional details about the hands and feet. Conditioning UV maps with human pose reduces invalid mappings and enhances anatomical plausibility. In addition, we highlight inconsistencies in the ground-truth annotations.