HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Panwang, Shen, Tingting, Li, Chenxin, Lin, Yunlong, Wen, Kairun, Zhao, Jingjing, Yuan, Yixuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908624422436864
author Pan, Panwang
Shen, Tingting
Li, Chenxin
Lin, Yunlong
Wen, Kairun
Zhao, Jingjing
Yuan, Yixuan
author_facet Pan, Panwang
Shen, Tingting
Li, Chenxin
Lin, Yunlong
Wen, Kairun
Zhao, Jingjing
Yuan, Yixuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00468
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
Pan, Panwang
Shen, Tingting
Li, Chenxin
Lin, Yunlong
Wen, Kairun
Zhao, Jingjing
Yuan, Yixuan
Computer Vision and Pattern Recognition
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.
title HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.00468