Research map / 3D vision / Gaussian splatting
LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
Jingzhi Bao, HONGZE CHEN, Lingting Zhu, Chenyu Liu, Runze Zhang, keyang luo, Zeyu HU, Weikai Chen, Yingda Yin, Xin Wang, Zehong Lin, Jun Zhang and 1 more
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 LumiTex instead of Hunyuan3D-2.1 (trained on private data) | PBR texture generation · Texture evaluation | FID: 196.6 -> 160.8 | Improved |
| use LumiTex instead of Hunyuan3D-2.1 | PBR texture generation · Relighting evaluation | FID: 103.7 -> 99.6 | Improved |
| use LumiTex instead of Hunyuan3D-2.1 | PBR texture generation · Relighting evaluation | LPIPS: 0.0808 -> 0.0831 | Hurt |
| use LumiTex instead of Hunyuan3D-2.1 | PBR texture generation · User study | overall quality rating: 3.69 -> 4.48 | Improved |
| add one-stage end-to-end generation instead of two-stage shaded images then PBR decomposition (ablation) | LumiTex · qualitative comparison | material accuracy | Improved |
| add disentangled multi-branch albedo and MR generation instead of joint multi-channel prediction (ablation) | LumiTex · qualitative comparison | material accuracy | Improved |
| add multi-view illumination context branch compared to a material-only variant (ablation) | LumiTex · qualitative comparison | metallic-roughness accuracy | 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.
- Paint-it — Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering (CVPR 2024) · better on 4 of 4 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
- TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- Material Palette: Extraction of Materials from a Single Image (CVPR 2024 · similarity 0.90)
- IntrinsiX: High-Quality PBR Generation using Image Priors (NeurIPS 2025 · similarity 0.90)
- MatSynth: A Modern PBR Materials Dataset (CVPR 2024 · similarity 0.87)
- MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation (CVPR 2025 · similarity 0.87)
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference (NeurIPS 2025 · 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.
