单图同时实现高精度人体重建与部位分割，打破任务孤立性
HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
- 融合几何先验与自监督语义先验，统一建模外观与人体部件语义
- 通过像素对齐聚合实现跨任务协同，提升纹理保真度与语义一致性
- 设计交互式标注流程解决3D人体数据稀缺问题，适合多任务生成应用
生成模型在3D人体重建方面已取得高保真度进展，但其在特定任务（如人体3D分割）中的实用性受限。本文提出HumanCrafter，一种统一框架，可从单张图像中以前馈方式联合建模外观与人体部件语义。具体而言，在重建阶段引入人体几何先验，在分割阶段引入自监督语义先验。为缓解标注3D人体数据集稀缺问题，进一步开发了交互式标注流程以生成高质量数据-标签对。像素对齐的聚合机制实现跨任务协同，多任务目标同步优化纹理建模保真度与语义一致性。大量实验表明，HumanCrafter在单图3D人体部位分割与3D人体重建上均超越现有最先进方法。
原文摘要 · Abstract (English)
Recent advances in generative models have achieved high-fidelity in 3D human reconstruction, yet their utility for specific tasks (e.g., human 3D segmentation) remains constrained. We propose HumanCrafter, a unified framework that enables the joint modeling of appearance and human-part semantics from a single image in a feed-forward manner. Specifically, we integrate human geometric priors in the reconstruction stage and self-supervised semantic priors in the segmentation stage. To address labeled 3D human datasets scarcity, we further develop an interactive annotation procedure for generating high-quality data-label pairs. Our pixel-aligned aggregation enables cross-task synergy, while the multi-task objective simultaneously optimizes texture modeling fidelity and semantic consistency. Extensive experiments demonstrate that HumanCrafter surpasses existing state-of-the-art methods in both 3D human-part segmentation and 3D human reconstruction from a single image.
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。