PulseAugur
中
实时 11:49:52
English(EN) Hi-TOPS: Hierarchical Topology-aware Scoring Prior for 3D Part Decomposition

新研究通过材料和拓扑感知推进三维部件分解 · 跟踪到2个来源

作者 PulseAugur 编辑部 · [3 个来源] ·

两篇新研究论文 PartMat 和 Hi-TOPS 引入了三维部件分解的新方法。PartMat 使用单一全局潜在表示和扩散模型专注于材料感知分解，旨在实现高效推理和准确的材料分配。另一方面，Hi-TOPS 采用层次化拓扑感知评分先验，通过聚合不同尺度的内在线索来实现稳定且可编辑的分解，而无需语义监督。 AI

影响 三维分解的进步可以改进虚拟环境和设计应用程序的内容创建流程。

排序理由 两篇在 arXiv 上发表的学术论文，介绍了三维部件分解的新方法。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新研究通过材料和拓扑感知推进三维部件分解 · 跟踪到2个来源

报道来源 [3]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    PartMat: Material-Aware 3D Part Decomposition with a Single Global Latent

    Part-level 3D generation has recently attracted increasing attention for producing structured and editable 3D assets. However, existing methods typically decompose objects according to functional semantics rather than the editable material boundaries (e.g., fabric, wood, metal) r…

  2. arXiv cs.CV TIER_1 English(EN) · Guangming Fu, Jin Song, Yiyun Fei, Guoqiu Li, Ruigao Yang, Jianan Jiang ·

    PartMat: Material-Aware 3D Part Decomposition with a Single Global Latent

    arXiv:2608.01825v1 Announce Type: new Abstract: Part-level 3D generation has recently attracted increasing attention for producing structured and editable 3D assets. However, existing methods typically decompose objects according to functional semantics rather than the editable m…

  3. arXiv cs.CV TIER_1 English(EN) · Ruoyu Wu, Zhenhong Sun, Xiaoming Gong, Yuxin Xian, Zhi Wang, Yawen Chen, Huadong Mo, Daoyi Dong ·

    Hi-TOPS: Hierarchical Topology-aware Scoring Prior for 3D Part Decomposition

    arXiv:2608.00767v1 Announce Type: cross Abstract: Accurate 3D part decomposition requires separating shapes into structurally meaningful components with precise boundaries while preserving articulation seams and thin attachments. Existing approaches often suffer from a structural…

相关实体

相关话题