Research map / 3D vision / NeRF and radiance fields
NeAR: Coupled Neural Asset-Renderer Stack
Hong Li, Chongjie Ye, Houyuan Chen, Weiqing Xiao, Ziyang Yan, Lixing Xiao, Zhaoxi Chen, Jianfeng Xiang, Shaocong Xu, Xuhui Liu, Yikai Wang, Baochang Zhang and 3 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 LH-SLAT instead of shaded SLAT as decoder input (ablation) | NeAR · Own test set | PSNR: 28.95 -> 32.02 | Improved |
| add base color SLAT to LH-SLAT (ablation) | NeAR · Own test set | PSNR: 32.02 -> 32.54 | Improved |
| increase lighting-aware decoder blocks from 1 to 6 (ablation) | NeAR decoder · Own test set | PSNR: 31.56 -> 32.54 | Improved |
| increase lighting-aware blocks from 6 to 9 (ablation) | NeAR decoder · Own test set | PSNR: 32.54 -> 32.56 | No clear effect |
| add intrinsic-aware decoder before lighting-aware decoder (ablation) | NeAR · Own test set | PSNR: 29.43 -> 32.54 | Improved |
| inject view embedding before lighting baking, drop SH color (ablation) | NeAR decoder · Own test set | PSNR: 29.82 -> 32.54 | Improved |
| replace DiffusionRenderer with NeAR for G-buffer forward rendering | NeAR · ADT | PSNR: 24.41 -> 29.15 | Improved |
| replace DiffusionRenderer with NeAR for unknown-lit relighting | NeAR · ADT | PSNR: 21.91 -> 21.95 | No clear effect |
| replace DiLightNet with NeAR for random-lit reconstruction | NeAR · ADT | PSNR: 21.11 -> 22.89 | Improved |
| replace Hunyuan3D-2.1 with NeAR for novel-view relighting | NeAR · Glossy Synthetic | PSNR: 22.26 -> 22.94 | Improved |
| replace DiffusionRenderer with NeAR for random-lit reconstruction | NeAR · DTC | PSNR: 23.70 -> 24.68 | Improved |
Closest papers by meaning
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.87)
- UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting (NeurIPS 2025 · similarity 0.86)
- Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models (CVPR 2025 · similarity 0.86)
- RNG: Relightable Neural Gaussians (CVPR 2025 · similarity 0.86)
- Global Latent Neural Rendering (CVPR 2024 · similarity 0.86)
- Structured 3D Latents for Scalable and Versatile 3D Generation (CVPR 2025 · 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.
