Research map / 3D vision / NeRF and radiance fields
Progressive Volume Distillation with Active Learning for Efficient NeRF Architecture Conversion
Shuangkang Fang, Yufeng Wang, Yi Yang, Weixin Xu, Heng Wang, Wenrui Ding, Shuchang Zhou
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 volume-aligned loss (ablation) | PVD-AL · TanksAndTemples VM-to-MLP | PSNR: 25.87 -> 26.71 | Improved |
| add RGB loss (ablation) | PVD-AL · TanksAndTemples VM-to-MLP | PSNR: 24.53 -> 26.71 | Improved |
| add density range constraint (ablation) | PVD-AL · TanksAndTemples VM-to-MLP | PSNR: 25.19 -> 26.71 | Improved |
| add block-wise distillation (ablation) | PVD-AL · TanksAndTemples VM-to-MLP | PSNR: 26.13 -> 26.71 | Improved |
| add important-ray active learning (ablation) | PVD-AL · TanksAndTemples VM-to-MLP | PSNR: 26.03 -> 26.71 | Improved |
| add important-pose active learning (ablation) | PVD-AL · TanksAndTemples VM-to-MLP | PSNR: 26.34 -> 26.71 | Improved |
| add important-point active learning (ablation) | PVD-AL · TanksAndTemples VM-to-MLP | PSNR: 26.52 -> 26.71 | Improved |
| raise MLP division position K from 2 to 6 (ablation) | PVD-AL · Synthetic-NeRF Hash-to-MLP | PSNR: 31.35 -> 31.70 | Improved |
| add active learning to KiloNeRF | KiloNeRF · Synthetic-NeRF | PSNR: 28.02 -> 29.21 | Improved |
| add active learning to R2L | R2L · Synthetic-NeRF | PSNR: 30.02 -> 30.35 | Improved |
| finetune distilled student on real data when student stronger than teacher (ablation) | s-VM from t-Tensors · Synthetic-NeRF | PSNR: 27.48 -> 31.5 | Improved |
| finetune distilled student when teacher is stronger (ablation) | s-VM from t-Hash · Synthetic-NeRF | PSNR: 31.83 -> 31.72 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- KiloNeRF — KiloNeRF: Speeding Up Neural Radiance Fields With Thousands of Tiny MLPs (ICCV 2021) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- One Is All: Bridging the Gap between Neural Radiance Fields Architectures with Progressive Volume Distillation (AAAI 2023 · similarity 0.94)
- NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion (ICML 2023 · similarity 0.89)
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis (ECCV 2020 · similarity 0.88)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.87)
- CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs (CVPR 2024 · similarity 0.87)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (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.
