HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
Panwang Pan, Tingting Shen, Chenxin Li, Yunlong Lin, Kairun Wen, Jingjing Zhao, Yixuan Yuan
Abstract
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**.
BibTeX
@inproceedings{
pan2025humancrafter,
title={HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation},
author={Panwang Pan and Tingting Shen and Chenxin Li and Yunlong Lin and Kairun Wen and Jingjing Zhao and Yixuan Yuan},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=EakfENFVPT}
}