Topology Sculptor, Shape Refiner: Discrete Diffusion Model for High-Fidelity 3D Meshes Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918172231204864 |
|---|---|
| author | Song, Kaiyu Lai, Hanjiang Zhang, Yaqing Cai, Chuangjian Yue, Yan Pan Kun Yin, Jian |
| author_facet | Song, Kaiyu Lai, Hanjiang Zhang, Yaqing Cai, Chuangjian Yue, Yan Pan Kun Yin, Jian |
| contents | In this paper, we introduce Topology Sculptor, Shape Refiner (TSSR), a novel method for generating high-quality, artist-style 3D meshes based on Discrete Diffusion Models (DDMs). Our primary motivation for TSSR is to achieve highly accurate token prediction while enabling parallel generation, a significant advantage over sequential autoregressive methods. By allowing TSSR to "see" all mesh tokens concurrently, we unlock a new level of efficiency and control. We leverage this parallel generation capability through three key innovations: 1) Decoupled Training and Hybrid Inference, which distinctly separates the DDM-based generation into a topology sculpting stage and a subsequent shape refinement stage. This strategic decoupling enables TSSR to effectively capture both intricate local topology and overarching global shape. 2) An Improved Hourglass Architecture, featuring bidirectional attention enriched by face-vertex-sequence level Rotational Positional Embeddings (RoPE), thereby capturing richer contextual information across the mesh structure. 3) A novel Connection Loss, which acts as a topological constraint to further enhance the realism and fidelity of the generated meshes. Extensive experiments on complex datasets demonstrate that TSSR generates high-quality 3D artist-style meshes, capable of achieving up to 10,000 faces at a remarkable spatial resolution of $1024^3$. The code will be released at: https://github.com/psky1111/Tencent-TSSR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21264 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Topology Sculptor, Shape Refiner: Discrete Diffusion Model for High-Fidelity 3D Meshes Generation Song, Kaiyu Lai, Hanjiang Zhang, Yaqing Cai, Chuangjian Yue, Yan Pan Kun Yin, Jian Computer Vision and Pattern Recognition In this paper, we introduce Topology Sculptor, Shape Refiner (TSSR), a novel method for generating high-quality, artist-style 3D meshes based on Discrete Diffusion Models (DDMs). Our primary motivation for TSSR is to achieve highly accurate token prediction while enabling parallel generation, a significant advantage over sequential autoregressive methods. By allowing TSSR to "see" all mesh tokens concurrently, we unlock a new level of efficiency and control. We leverage this parallel generation capability through three key innovations: 1) Decoupled Training and Hybrid Inference, which distinctly separates the DDM-based generation into a topology sculpting stage and a subsequent shape refinement stage. This strategic decoupling enables TSSR to effectively capture both intricate local topology and overarching global shape. 2) An Improved Hourglass Architecture, featuring bidirectional attention enriched by face-vertex-sequence level Rotational Positional Embeddings (RoPE), thereby capturing richer contextual information across the mesh structure. 3) A novel Connection Loss, which acts as a topological constraint to further enhance the realism and fidelity of the generated meshes. Extensive experiments on complex datasets demonstrate that TSSR generates high-quality 3D artist-style meshes, capable of achieving up to 10,000 faces at a remarkable spatial resolution of $1024^3$. The code will be released at: https://github.com/psky1111/Tencent-TSSR. |
| title | Topology Sculptor, Shape Refiner: Discrete Diffusion Model for High-Fidelity 3D Meshes Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.21264 |