Research map / 3D vision / Face and shape
DANTE-W: Diffuse Albedo Neural Texturing in the Wild
Guangyu Wang, Tianheng Lu, Ruqi Huang, Lu Fang
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 physically principled neural rendering (PR) on top of lifted diffusion priors (ablation) | Ours+DR · GigaLit synthetic diffuse albedo | PSNR: 25.69 -> 25.99 | Improved |
| add physically principled neural rendering (PR) on top of lifted diffusion priors (ablation) | Ours+DR · GigaLit synthetic diffuse albedo | LPIPS: 0.115 -> 0.091 | Improved |
| add physically principled neural rendering (PR) on top of lifted diffusion priors (ablation) | Ours+DR · GigaLit synthetic relighting | PSNR: 27.45 -> 27.77 | Improved |
| add physically principled neural rendering (PR) on top of lifted diffusion priors (ablation) | Ours+DR · GigaLit synthetic relighting | LPIPS: 0.092 -> 0.071 | Improved |
| add physically principled neural rendering (PR) on top of lifted diffusion priors (ablation) | Ours+RGB<->X · GigaLit synthetic diffuse albedo | PSNR: 25.32 -> 25.50 | Improved |
| add physically principled neural rendering (PR) on top of lifted diffusion priors (ablation) | Ours+RGB<->X · GigaLit synthetic diffuse albedo | LPIPS: 0.120 -> 0.093 | Improved |
| add physically principled neural rendering (PR) on top of lifted diffusion priors (ablation) | Ours+RGB<->X · GigaLit synthetic relighting | LPIPS: 0.099 -> 0.076 | Improved |
| lift DiffusionRenderer albedo into a neural texture instead of using raw diffusion output | DiffusionRenderer · GigaLit synthetic diffuse albedo | PSNR: 23.36 -> 25.99 | Improved |
| lift RGB<->X albedo into a neural texture instead of using raw diffusion output | RGB<->X · GigaLit synthetic diffuse albedo | PSNR: 21.65 -> 25.50 | Improved |
| use neural texture relighting instead of raw DiffusionRenderer | DiffusionRenderer · GigaLit synthetic relighting | PSNR: 21.64 -> 27.77 | Improved |
| use neural texture relighting instead of raw RGB<->X | RGB<->X · GigaLit synthetic relighting | PSNR: 20.30 -> 27.45 | Improved |
| use DANTE-W instead of vanilla mesh texturing | Metashape Pro · GigaLit synthetic diffuse albedo | PSNR: 21.50 -> 25.99 | 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.
- LightSwitch — LightSwitch: Multi-view Relighting with Material-guided Diffusion (ICCV 2025) · 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
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · similarity 0.87)
- NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild (NeurIPS 2021 · similarity 0.87)
- Inverse Rendering of Translucent Objects Using Physical and Neural Renderers (CVPR 2023 · similarity 0.87)
- Light Sampling Field and BRDF Representation for Physically-based Neural Rendering (ICLR 2023 · similarity 0.87)
- RobIR: Robust Inverse Rendering for High-Illumination Scenes (NeurIPS 2024 · similarity 0.85)
- GOATex: Geometry & Occlusion-Aware Texturing (NeurIPS 2025 · 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.
