Research map / 3D vision / NeRF and radiance fields
OmniRen: Neural Rendering wih Heterogeneous Scene Primitives
Chong Zeng, Yue Dong, Pieter Peers, lvmin zhang, Maneesh Agrawala
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 attention sink to windowed attention (ablation) | RenderFormer-V2 · Synthetic random scenes, 16k primitives (stage 4) | PSNR: 27.36 -> 28.25 | Improved |
| add sliding window attention to attention sink (ablation) | RenderFormer-V2 · Synthetic random scenes, 16k primitives (stage 4) | PSNR: 26.92 -> 28.25 | Improved |
| add light source tokens to attention sink (ablation) | RenderFormer-V2 · Synthetic random scenes, 16k primitives (stage 4) | PSNR: 27.40 -> 28.25 | Improved |
| add light source tokens to attention sink (ablation) | RenderFormer-V2 · Synthetic random scenes, 16k primitives (stage 4) | LPIPS: 0.1081 -> 0.0997 | Mixed |
| add summarization tokens to attention sink (ablation) | RenderFormer-V2 · Synthetic random scenes, 16k primitives (stage 4) | PSNR: 27.09 -> 28.25 | Improved |
| add both light and summary tokens to sink (ablation) | RenderFormer-V2 · Synthetic random scenes, 16k primitives (stage 4) | PSNR: 26.13 -> 28.25 | Improved |
| use sparse attention instead of full attention (ablation) | RenderFormer-V2 · Synthetic random scenes, 16k primitives (stage 4) | PSNR: 27.91 -> 28.25 | Improved |
| fewer summarization tokens (#seq/128 vs default) (ablation) | RenderFormer-V2 · Synthetic random scenes, 16k primitives (stage 4) | PSNR: 28.25 -> 26.48 | Hurt |
| more summarization tokens (#seq/32 vs default) (ablation) | RenderFormer-V2 · Synthetic random scenes, 16k primitives (stage 4) | PSNR: 28.25 -> 27.78 | No clear effect |
| sparse attention vs RenderFormer brute-force attention at 83.2k triangles | RenderFormer-V2 · Large scenes (qualitative) | image quality | Improved |
Closest papers by meaning
- ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting (ICCV 2023 · similarity 0.90)
- Light Field Neural Rendering (CVPR 2022 · similarity 0.89)
- Neural Voxel Renderer: Learning an Accurate and Controllable Rendering Tool (CVPR 2020 · similarity 0.88)
- Inverse Rendering of Translucent Objects Using Physical and Neural Renderers (CVPR 2023 · similarity 0.88)
- Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models (CVPR 2025 · similarity 0.87)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (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.
