Research map / 3D vision / NeRF and radiance fields
Compressing Volumetric Radiance Fields to 1 MB
Read the paperCheck 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 |
|---|---|---|---|
| Compress DVGO with voxel pruning, vector quantization, joint finetuning, and weight quantization | DVGO · Synthetic-NeRF | model size: 105.9 -> 1.4 | Helped |
| Compress Plenoxels with VQRF | Plenoxels · Synthetic-NeRF | model size: 259.8 -> 13.7 | Helped |
| Compress TensoRF with VQRF | TensoRF · Synthetic-NeRF | model size: 67.6 -> 3.6 | Helped |
| Compress DVGO with VQRF | DVGO · Synthetic-NeRF | PSNR: 31.90 -> 31.77 | Hurt |
| Compress Plenoxels with VQRF | Plenoxels · Synthetic-NeRF | PSNR: 31.71 -> 31.53 | Hurt |
| Compress TensoRF with VQRF | TensoRF · Synthetic-NeRF | PSNR: 33.09 -> 32.86 | Hurt |
| Add voxel pruning (ablation) | DVGO · Synthetic-NeRF | model size: 105.9 -> 19.0 | Helped |
| Add vector quantization after pruning (ablation) | DVGO · Synthetic-NeRF | PSNR: 31.88 -> 31.32 | Hurt |
| Add joint finetuning after vector quantization (ablation) | DVGO · Synthetic-NeRF | PSNR: 31.32 -> 31.79 | Helped |
| Add weight quantization (ablation) | DVGO · Synthetic-NeRF | model size: 4.8 -> 1.4 | Helped |
| Increase codebook size from 4096 to 16384 (ablation) | VQ-DVGO · Synthetic-NeRF | PSNR: 31.77 -> 31.81 | Helped |
| Increase codebook size from 4096 to 16384 (ablation) | VQ-DVGO · Synthetic-NeRF | model size: 1.431 -> 1.630 | Hurt |
Closest papers by meaning
- Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering (CVPR 2025 · similarity 0.90)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.89)
- Neural NeRF Compression (ICML 2024 · similarity 0.87)
- CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs (CVPR 2024 · similarity 0.87)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.87)
- Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency (CVPR 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.