Research map / 3D vision / 3D generation
Text2Tex: Text-driven Texture Synthesis via Diffusion Models
Dave Zhenyu Chen, Yawar Siddiqui, Hsin-Ying Lee, Sergey Tulyakov, Matthias Nießner
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 |
|---|---|---|---|
| use Text2Tex instead of best text-driven baseline | CLIPMesh · Objaverse subset | FID: 43.25 -> 35.68 | Improved |
| use Text2Tex instead of Texturify GAN | Texturify · ShapeNet cars | FID: 59.55 -> 46.91 | Improved |
| add depth-aware inpainting with generation mask (ablation) | Depth2Img generation · Objaverse subset | FID: 39.88 -> 38.19 | Improved |
| add texture updating from better viewing angles (ablation) | Depth2Img + inpainting · Objaverse subset | FID: 38.19 -> 37.09 | Improved |
| add refinement stage with 20 automatically selected viewpoints (ablation) | Text2Tex generation · Objaverse subset | FID: 37.09 -> 35.68 | Improved |
| increase refinement views from 5 to 20 (ablation) | Text2Tex refinement · Objaverse subset | KID x10^-3: 8.31 -> 7.74 | Improved |
Later papers that compared with this method
16 later accepted papers report Text2Tex as a baseline in their results tables; 16 of them report a better number on most of the results they share with it.
- GaussianGrow: Geometry-aware Gaussian Growing from 3D Point Clouds with Text Guidance (CVPR 2026 · better on 3 of 3 shared results)
- GAP: Gaussianize Any Point Clouds with Text Guidance (ICCV 2025 · better on 8 of 8 shared results)
- RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis (ICCV 2025 · better on 3 of 4 shared results)
- Material Anything: Generating Materials for Any 3D Object via Diffusion (CVPR 2025 · better on 2 of 2 shared results)
- TexTailor: Customized Text-aligned Texturing via Effective Resampling (ICLR 2025 · better on 2 of 2 shared results)
- MV-Adapter: Multi-View Consistent Image Generation Made Easy (ICCV 2025 · better on 1 of 1 shared result)
- Learning Pseudo 3D Guidance for View-consistent Texturing with 2D Diffusion (ECCV 2024 · better on 5 of 5 shared results)
- Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models (CVPR 2024 · better on 4 of 4 shared results)
8 more not listed.
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.
- Text2Mesh — Text2Mesh: Text-Driven Neural Stylization for Meshes (CVPR 2022) · better on 2 of 2 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
- TexTailor: Customized Text-aligned Texturing via Effective Resampling (ICLR 2025 · similarity 0.91)
- GenesisTex: Adapting Image Denoising Diffusion to Texture Space (CVPR 2024 · similarity 0.90)
- ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (CVPR 2024 · similarity 0.90)
- SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors (CVPR 2024 · similarity 0.90)
- Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering (CVPR 2024 · similarity 0.89)
- DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors (CVPR 2024 · similarity 0.89)
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.
