Research map / 3D vision / Face and shape
Text2Mesh: Text-Driven Neural Stylization for Meshes
Oscar Michel, Roi Bar-On, Richard Liu, Sagie Benaim, Rana Hanocka
Check 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 Text2Mesh instead of the VQGAN baseline | Text-driven mesh stylization · User study (Q1): Overall | mean opinion score: 2.83 -> 3.90 | Improved |
| Use Text2Mesh instead of the VQGAN baseline | Text-driven mesh stylization · User study (Q2): Content | mean opinion score: 3.60 -> 4.04 | Improved |
| Use Text2Mesh instead of the VQGAN baseline | Text-driven mesh stylization · User study (Q3): Style | mean opinion score: 2.59 -> 3.91 | Improved |
| Add the neural style field network rather than directly optimizing vertex colors and displacements (ablation) | Text2Mesh · Text-driven mesh stylization | visual quality | Improved |
| Add random 2D augmentations (ablation) | Text2Mesh · Text-driven mesh stylization | alignment with target text | Improved |
| Add Fourier feature positional encoding (ablation) | Text2Mesh · Text-driven mesh stylization | fine-grained style detail | Improved |
| Add cropping to the local image augmentation (ablation) | Text2Mesh · Text-driven mesh stylization | fine-grained style detail | Improved |
| Add the geometry-only component to the similarity loss (ablation) | Text2Mesh · Text-driven mesh stylization | geometric refinement | Improved |
| Add the input mesh as a geometric prior (ablation) | Text2Mesh · Text-driven mesh stylization | preservation of global content structure | Improved |
| Learn color and geometry together rather than geometry alone (ablation) | Text2Mesh · Text-driven mesh stylization | geometry quality | Improved |
| Learn geometry and color together rather than color alone (ablation) | Text2Mesh · Text-driven mesh stylization | realism of texture and geometry | Improved |
| Use five or more sampled views rather than fewer sampled views (ablation) | Text2Mesh · Text-driven mesh stylization | stylization quality | No clear effect |
Later papers that compared with this method
8 later accepted papers report Text2Mesh as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.
- Image-Guided Geometric Stylization of 3D Meshes (CVPR 2026 · better on 1 of 1 shared result)
- TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes (CVPR 2024 · better on 4 of 4 shared results)
- UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures (CVPR 2024 · better on 2 of 2 shared results)
- LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching (CVPR 2024 · better on 1 of 1 shared result)
- Vox-E: Text-Guided Voxel Editing of 3D Objects (ICCV 2023 · better on 0 of 4 shared results)
- Text2Tex: Text-driven Texture Synthesis via Diffusion Models (ICCV 2023 · better on 2 of 2 shared results)
- X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance (ICCV 2023 · better on 2 of 2 shared results)
- TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition (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
- X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance (ICCV 2023 · similarity 0.89)
- Advances in 3D Neural Stylization: A Survey (IJCV 2025 · similarity 0.88)
- Image-Guided Geometric Stylization of 3D Meshes (CVPR 2026 · similarity 0.87)
- TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes (CVPR 2024 · similarity 0.87)
- Geometry in Style: 3D Stylization via Surface Normal Deformation (CVPR 2025 · similarity 0.85)
- TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields (ICLR 2024 · similarity 0.85)
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.
