Research map / 3D vision / 3D generation
RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis
Yifei Feng, Mingxin Yang, Shuhui Yang, Sheng Zhang, Jiaao Yu, Zibo Zhao, Yuhong Liu, Jie Jiang, Chunchao Guo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add 3D-aware RoPE in multi-view attention (ablation) | RomanTex · multi-view consistency (qualitative) | visual consistency | Improved |
| add decoupled reference branch (MVA dropout) (ablation) | RomanTex · back-view texture (qualitative) | visual quality | Improved |
| add geometry-related CFG at inference (ablation) | RomanTex · geometry alignment (qualitative) | visual alignment | Improved |
| RomanTex vs HY3D-2.0 multi-view baseline | HY3D-2.0 · Text-to-texture | CLIP-FID: 26.44 -> 24.78 | Improved |
| RomanTex vs HY3D-2.0 multi-view baseline | HY3D-2.0 · Text-to-texture | CMMD: 2.318 -> 2.191 | Improved |
| RomanTex vs HY3D-2.0 multi-view baseline | HY3D-2.0 · Text-to-texture | LPIPS: 0.136 -> 0.121 | Improved |
| RomanTex vs Text2tex on text alignment | Text2tex · Text-to-texture | CLIP-T: 0.318 vs 0.308 | No clear effect |
| RomanTex vs HY3D-2.0 | HY3D-2.0 · Image-to-texture | CLIP-FID: 26.439 -> 24.78 | Improved |
| RomanTex vs Paint3D-IPA on image fidelity | Paint3D-IPA · Image-to-texture | CLIP-I: 0.998 vs 0.891 | Hurt |
| RomanTex vs HY3D-2.0 in user study | HY3D-2.0 · Image-to-texture user study | overall quality Q (%): 20.7 -> 63.9 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Paint3D — Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models (CVPR 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors (CVPR 2024 · similarity 0.88)
- FlexiTex: Enhancing Texture Generation via Visual Guidance (AAAI 2025 · similarity 0.88)
- TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features (CVPR 2025 · similarity 0.87)
- GenesisTex: Adapting Image Denoising Diffusion to Texture Space (CVPR 2024 · similarity 0.87)
- Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering (CVPR 2024 · similarity 0.86)
- TexTailor: Customized Text-aligned Texturing via Effective Resampling (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
