Research map / 3D vision / Face and shape
TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition
Yongwei Chen, Rui Chen, Jiabao Lei, Yabin Zhang, Kui Jia
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 |
|---|---|---|---|
| Replace vertex-displacement stylization (Text2Mesh) with SVBRDF, normal map and lighting disentanglement | 3D mesh stylization · User study Q1 overall naturalness | mean opinion score: 3.30 -> 4.02 | Improved |
| Replace vertex-displacement stylization (Text2Mesh) with TANGO | 3D mesh stylization · User study Q2 content match | mean opinion score: 3.53 -> 3.98 | Improved |
| Replace Text2Mesh with TANGO | 3D mesh stylization · User study Q3 style match | mean opinion score: 3.42 -> 3.94 | Improved |
| Add spatially varying specular and roughness prediction (ablation) | TANGO · candle made of wicker (qualitative) | visual realism of highlights | Improved |
| Add normal estimation network (ablation) | TANGO · candle made of wicker (qualitative) | geometric detail | Improved |
| Add positional encoding for SVBRDF and normal networks (ablation) | TANGO · candle made of wicker (qualitative) | high-frequency detail | Improved |
| Add local crop augmentation (ablation) | TANGO · candle made of wicker (qualitative) | stylization quality | Improved |
| Change background among black, white, random Gaussian (ablation) | TANGO · stylization | stylization quality | No clear effect |
| Use TANGO instead of Text2Mesh on meshes downsampled to 5,000 faces | low-quality meshes · lamp and alien meshes (qualitative) | robustness | Improved |
Later papers that compared with this method
2 later accepted papers report TANGO as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes (CVPR 2024 · better on 4 of 4 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)
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 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
- Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles (NeurIPS 2025 · similarity 0.90)
- FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields (AAAI 2024 · similarity 0.88)
- ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
- Morpheus: Text-Driven 3D Gaussian Splat Shape and Color Stylization (CVPR 2025 · similarity 0.88)
- Multi-StyleGS: Stylized Gaussian Splatting with Multiple Styles (AAAI 2025 · similarity 0.88)
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example (CVPR 2024 · similarity 0.87)
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.
