用人体姿态约束提升三维人体贴图的合理性与精度
Human Pose-Constrained UV Map Estimation
- 将2D人体姿态融入像素到顶点的映射过程，增强全局一致性
- 在DensePose COCO上显著减少无效映射，提升解剖合理性
- 适合关注人体动作分析与高精度贴图的应用场景
UV贴图估计用于计算机视觉中对人体姿态或动作的精细化分析。以往方法独立比较像素描述子进行像素到体模型顶点的分配，未强制全局一致性和解剖合理性。本文提出姿态约束的连续表面嵌入（PC-CSE），将估计的2D人体姿态整合进像素-顶点映射过程。姿态提供全局解剖约束，使UV贴图在保持局部精度的同时具备更高一致性。在DensePose COCO数据集上的评估显示，无论采用何种2D人体姿态模型，均实现稳定提升；全身姿态通过引入手部和足部细节，提供更优约束。以人体姿态为条件可有效减少无效映射，增强解剖合理性。此外，本文还揭示了真实标注中的不一致性问题。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。