{"ID":2882555,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.11106","arxiv_id":"2508.11106","title":"HierOctFusion: Multi-scale Octree-based 3D Shape Generation via Part-Whole-Hierarchy Message Passing","abstract":"3D content generation remains a fundamental yet challenging task due to the inherent structural complexity of 3D data. While recent octree-based diffusion models offer a promising balance between efficiency and quality through hierarchical generation, they often overlook two key insights: 1) existing methods typically model 3D objects as holistic entities, ignoring their semantic part hierarchies and limiting generalization; and 2) holistic high-resolution modeling is computationally expensive, whereas real-world objects are inherently sparse and hierarchical, making them well-suited for layered generation. Motivated by these observations, we propose HierOctFusion, a part-aware multi-scale octree diffusion model that enhances hierarchical feature interaction for generating fine-grained and sparse object structures. Furthermore, we introduce a cross-attention conditioning mechanism that injects part-level information into the generation process, enabling semantic features to propagate effectively across hierarchical levels from parts to the whole. Additionally, we construct a 3D dataset with part category annotations using a pre-trained segmentation model to facilitate training and evaluation. Experiments demonstrate that HierOctFusion achieves superior shape quality and efficiency compared to prior methods.","short_abstract":"3D content generation remains a fundamental yet challenging task due to the inherent structural complexity of 3D data. While recent octree-based diffusion models offer a promising balance between efficiency and quality through hierarchical generation, they often overlook two key insights: 1) existing methods typically...","url_abs":"https://arxiv.org/abs/2508.11106","url_pdf":"https://arxiv.org/pdf/2508.11106v1","authors":"[\"Xinjie Gao\",\"Bi'an Du\",\"Wei Hu\"]","published":"2025-08-14T23:12:18Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}