Research map / 3D vision / NeRF and radiance fields
Binary Radiance Fields
Seungjoo Shin, Jaesik Park
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 2D-3D hybrid grid instead of tri-plane only (ablation) | Ours-B2 · Synthetic-NeRF | PSNR: 31.44 -> 32.64 | Improved |
| use 2D-3D hybrid grid instead of voxel only (ablation) | Ours-B2 · Synthetic-NeRF | PSNR: 32.35 -> 32.64 | Improved |
| use hybrid grid instead of tri-plane (ablation) | Ours-B2 · Tanks and Temples | PSNR: 27.97 -> 28.49 | Improved |
| use hybrid grid instead of voxel (ablation) | Ours-B2 · Synthetic-NSVF | PSNR: 35.10 -> 35.70 | Improved |
| add sparsity loss (ablation) | Ours-B2 · Synthetic-NeRF | inference speed: 3.3 fps -> 3.8 fps | Improved |
| add sparsity loss (ablation) | Ours-B8 · Synthetic-NeRF | inference speed: 2.2 fps -> 2.7 fps | Improved |
| add sparsity loss (ablation) | Ours-B2 · Synthetic-NeRF | train time: 6.4 m -> 6.1 m | Improved |
| add sparsity loss (ablation) | Ours-B8 · Synthetic-NeRF | PSNR: 33.60 -> 33.59 | No clear effect |
| add sparsity loss (ablation) | Ours-B2 · Synthetic-NeRF | PSNR: 32.69 -> 32.64 | No clear effect |
| increase hash table size from {2^17,2^19} to {2^21,2^23} (ablation) | Ours F=1 · Synthetic-NeRF | PSNR: 31.53 -> 31.93 | Improved |
| reduce hash table to {2^13,2^15} (ablation) | Ours F=1 · Synthetic-NeRF | PSNR: 31.53 -> 29.20 | Hurt |
| increase feature dimension F from 2 to 8 (ablation) | Ours-B · Synthetic-NeRF | PSNR: 32.64 -> 33.59 | Improved |
Closest papers by meaning
- NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation (CVPR 2024 · similarity 0.88)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.87)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.87)
- Neural NeRF Compression (ICML 2024 · similarity 0.87)
- CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis (AAAI 2025 · similarity 0.86)
- VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams (CVPR 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.
