{"ID":2872637,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.08643","arxiv_id":"2509.08643","title":"X-Part: high fidelity and structure coherent shape decomposition","abstract":"Generating 3D shapes at part level is pivotal for downstream applications such as mesh retopology, UV mapping, and 3D printing. However, existing part-based generation methods often lack sufficient controllability and suffer from poor semantically meaningful decomposition. To this end, we introduce X-Part, a controllable generative model designed to decompose a holistic 3D object into semantically meaningful and structurally coherent parts with high geometric fidelity. X-Part exploits the bounding box as prompts for the part generation and injects point-wise semantic features for meaningful decomposition. Furthermore, we design an editable pipeline for interactive part generation. Extensive experimental results show that X-Part achieves state-of-the-art performance in part-level shape generation. This work establishes a new paradigm for creating production-ready, editable, and structurally sound 3D assets. Codes will be released for public research.","short_abstract":"Generating 3D shapes at part level is pivotal for downstream applications such as mesh retopology, UV mapping, and 3D printing. However, existing part-based generation methods often lack sufficient controllability and suffer from poor semantically meaningful decomposition. To this end, we introduce X-Part, a controllab...","url_abs":"https://arxiv.org/abs/2509.08643","url_pdf":"https://arxiv.org/pdf/2509.08643v2","authors":"[\"Xinhao Yan\",\"Jiachen Xu\",\"Yang Li\",\"Changfeng Ma\",\"Yunhan Yang\",\"Chunshi Wang\",\"Zibo Zhao\",\"Zeqiang Lai\",\"Yunfei Zhao\",\"Zhuo Chen\",\"Chunchao Guo\"]","published":"2025-09-10T14:37:02Z","proceeding":"cs.GR","tasks":"[\"cs.GR\",\"cs.CV\"]","methods":"[]","has_code":false}