{"ID":2847216,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.00468","arxiv_id":"2511.00468","title":"HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation","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.","short_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...","url_abs":"https://arxiv.org/abs/2511.00468","url_pdf":"https://arxiv.org/pdf/2511.00468v1","authors":"[\"Panwang Pan\",\"Tingting Shen\",\"Chenxin Li\",\"Yunlong Lin\",\"Kairun Wen\",\"Jingjing Zhao\",\"Yixuan Yuan\"]","published":"2025-11-01T09:29:36Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}