[论文] Dense4D: Pixel-Level 4D Human Correspondence

论文概要

研究领域: CV 作者: Rıza Alp Güler 发布时间: 2026-10-15 arXiv: 2610.22325

中文摘要

在 4D 中重建人体运动需要识别经过关节活动、变形和可见性变化的相同表面点。我们引入 Dense4D，这是我们所知第一个专门用于从一组单目 RGB 图像中实现跨身体、服装和头发的密集 4D 对应的前馈模型，无需身体模板。Dense4D 联合处理以人物为中心的裁剪图像，预测人体点图（HPM）和每幅图像的深度。HPM 为每个人物像素分配其观测表面点在共同参考时间的 3D 位置，支持非模态对应：参考图像中隐藏的点可以从其他帧的观测中定位。在真实人体上的实验表明，其跟踪精度和与扫描表面的一致性大幅优于评估的基线。项目页面：https://alpguler.com/dense4d

原文摘要

Reconstructing human motion in 4D requires identifying the same surface points through articulation, deformation and changes in visibility. We introduce Dense4D, to our knowledge the first feed-forward model dedicated to dense 4D correspondence across the body, clothing and hair from a set of monocular RGB images, without a body template. Trained specifically for human geometry, Dense4D jointly processes person-centred crops with known image-to-crop transforms to predict Human Point Maps (HPMs) and depth for each image. An HPM assigns each person pixel the 3D position of its observed surface point at a common reference time. These maps support amodal correspondence: points hidden in the reference image can be localised from observations in other frames. Matching HPM coordinates across crop...

#论文 #arXiv #CV #小凯