Research map / 3D vision / Face and shape
Mesh2Tex: Generating Mesh Textures from Image Queries
Alexey Bokhovkin, Shubham Tulsiani, Angela Dai
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 patch style loss to texture transfer optimization (ablation) | Mesh2Tex · Unaligned ShapeNet chairs | FID: 143.5 -> 121.1 | Improved |
| add NOC guidance to patch style loss (ablation) | Mesh2Tex · Unaligned ShapeNet chairs | FID: 124.3 -> 121.1 | Improved |
| add surface feature optimization after latent code optimization (ablation) | Mesh2Tex · Unaligned ShapeNet chairs | FID: 127.1 -> 121.1 | Improved |
| add NOC guidance to patch style loss (ablation) | Mesh2Tex · Unaligned ShapeNet chairs | CLIP: 91.09 -> 91.57 | Improved |
| use hybrid mesh-field representation instead of per-face color (Texturify) | Mesh2Tex · Unconditional generation, Cars | FID: 59.55 -> 41.35 | Improved |
| use hybrid mesh-field representation instead of per-face color (Texturify) | Mesh2Tex · Unconditional generation, Chairs | FID: 31.08 -> 30.01 | Improved |
| apply Mesh2Tex under texture transfer to different geometry | Mesh2Tex · ShapeNet cars aligned vs transfer | FID: 165.5 -> 194.5 | Hurt |
| Mesh2Tex versus Texturify on aligned exact-geometry car query | Mesh2Tex · ShapeNet cars | LPIPS: 14.69 -> 14.77 | No clear effect |
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.
- GET3D — GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images (NeurIPS 2022) · 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
- Leveraging 2D Data to Learn Textured 3D Mesh Generation (CVPR 2020 · similarity 0.92)
- Convolutional Generation of Textured 3D Meshes (NeurIPS 2020 · similarity 0.92)
- TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features (CVPR 2025 · similarity 0.91)
- GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images (NeurIPS 2022 · similarity 0.90)
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors (ICLR 2024 · similarity 0.89)
- MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation (CVPR 2025 · 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.
