Research map / 3D vision / NeRF and radiance fields
A Neural Rendering Framework for Free-Viewpoint Relighting
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 physically based image formation with learnable albedo, illumination, and light transport rather than a direct appearance renderer | RNR · View synthesis across seven objects | PSNR/SSIM: 31.53/0.93 -> 39.08/0.98 | Helped |
| Use RNR rather than DeferredNR with sparse training views | View synthesis · Bunny and Earth (sparse inputs) | PSNR/SSIM: 24.38/0.81 -> 30.87/0.94 | Helped |
| Add GCN geometric features to the U-Net (ablation) | RNR · Synthetic relighting: Earth, Bunny, Material, Horse | PSNR/SSIM: 25.87/0.93 -> 26.29/0.94; 24.96/0.91 -> 25.13/0.92; 27.67/0.81 -> 28.04/0.89; 28.76/0.93 -> 29.56/0.94 | Helped |
| Remove light-transport chromaticity loss (ablation) | RNR · Relighting | PSNR/SSIM | Hurt |
| Remove illumination loss (ablation) | RNR · Relighting | PSNR/SSIM | Hurt |
Closest papers by meaning
- IllumiNeRF: 3D Relighting Without Inverse Rendering (NeurIPS 2024 · similarity 0.90)
- ROGR: Relightable 3D Objects using Generative Relighting (NeurIPS 2025 · similarity 0.89)
- UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting (NeurIPS 2025 · similarity 0.88)
- SyncLight: Single-Edit Multi-View Relighting (NeurIPS 2026 · similarity 0.88)
- Neural Gaffer: Relighting Any Object via Diffusion (NeurIPS 2024 · similarity 0.87)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 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.