Research map / 3D vision / NeRF and radiance fields
3D Scene Creation and Rendering via Rough Meshes: A Lighting Transfer Avenue
Bowen Cai, Yujie Li, Yuqin Liang, Rongfei Jia, Binqiang Zhao, Mingming Gong, Huan Fu
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 L1 photometric loss with L_FR (ablation) | LighTNet · 3DF-Lighting test set | PSNR: 28.37 -> 29.06 | Improved |
| add L_DSSIM to L_FR (ablation) | LighTNet · 3DF-Lighting test set | PSNR: 29.06 -> 29.83 | Improved |
| add L_Lab to L_FR + L_DSSIM (ablation) | LighTNet · 3DF-Lighting test set | PSNR: 29.83 -> 30.17 | Improved |
| add L_Lab to L_FR + L_DSSIM (ablation) | LighTNet · 3DF-Lighting test set | Lab Angle: 0.3317 -> 0.3137 | Improved |
| add auxiliary L1 loss to full objective (ablation) | LighTNet · 3DF-Lighting test set | PSNR: 30.17 -> 29.37 | Hurt |
| add auxiliary L1 loss to full objective (ablation) | LighTNet · 3DF-Lighting test set | L1-Norm: 0.0219 -> 0.0240 | Hurt |
| add reflection strength R to D*S (ablation) | LighTNet · 3DF-Lighting test set | PSNR: 28.46 -> 28.83 | Improved |
| add residual alpha inside the product (D+R+alpha)*S instead of (D+R)*S (ablation) | LighTNet · 3DF-Lighting test set | PSNR: 28.83 -> 30.17 | Improved |
| apply alpha as a product term instead of an additive term (ablation) | LighTNet · 3DF-Lighting test set | PSNR: 29.45 -> 30.17 | Improved |
| learn shading residual S'_r instead of using rough shading S' (ablation) | LighTNet · 3DF-Lighting test set | PSNR: 28.70 -> 30.17 | Improved |
| predict smooth shading S* directly instead of residual (ablation) | LighTNet · 3DF-Lighting test set | PSNR: 28.70 -> 29.35 | Improved |
| learn residual S'_r instead of predicting S* directly (ablation) | LighTNet · 3DF-Lighting test set | PSNR: 29.35 -> 30.17 | Improved |
Closest papers by meaning
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.89)
- Geo-NI: Geometry-Aware Neural Interpolation for Light Field Rendering (TPAMI 2025 · similarity 0.88)
- ROGR: Relightable 3D Objects using Generative Relighting (NeurIPS 2025 · similarity 0.87)
- VMINer: Versatile Multi-view Inverse Rendering with Near- and Far-field Light Sources (CVPR 2024 · similarity 0.87)
- IllumiNeRF: 3D Relighting Without Inverse Rendering (NeurIPS 2024 · similarity 0.87)
- Real3D: The Curious Case of Neural Scene Degeneration (AAAI 2024 · similarity 0.86)
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.
