Research map / 3D vision / NeRF and radiance fields
WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields
Muyu Xu, Fangneng Zhan, Jiahui Zhang, Yingchen Yu, Xiaoqin Zhang, Christian Theobalt, Ling Shao, Shijian Lu
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 Wavelet MVS (WMVS) (ablation) | GeoNeRF baseline · DTU | PSNR: 27.67 -> 27.97 | Improved |
| add Wavelet MVS (WMVS) (ablation) | GeoNeRF baseline · NeRF Synthetic | PSNR: 24.80 -> 24.63 | Hurt |
| add Wavelet MVS (WMVS) (ablation) | GeoNeRF baseline · LLFF | PSNR: 23.22 -> 23.23 | No clear effect |
| add Frequency-guided Sampling Strategy (FSS) (ablation) | WMVS model · DTU | PSNR: 27.97 -> 28.90 | Improved |
| add Frequency-guided Sampling Strategy (FSS) (ablation) | WMVS model · NeRF Synthetic | LPIPS: 0.183 -> 0.119 | Improved |
| add Hybrid Neural Renderer (HNR) (ablation) | WMVS + FSS model · DTU | PSNR: 28.90 -> 29.16 | Improved |
| add Hybrid Neural Renderer (HNR) (ablation) | WMVS + FSS model · LLFF | LPIPS: 0.227 -> 0.206 | Improved |
| add Weighted Frequency Loss (WFL) (ablation) | WMVS + FSS + HNR model · DTU | PSNR: 29.16 -> 29.55 | Improved |
| add WFL (ablation) | WMVS + FSS + HNR model · LLFF | LPIPS: 0.206 -> 0.212 | Hurt |
| train from scratch end-to-end vs pretrained CasMVSNet checkpoint | GeoNeRF · DTU | PSNR: 29.02 -> 27.67 | Hurt |
| compare WaveNeRF with pretrained-MVS GeoNeRF* | WaveNeRF · LLFF | PSNR: 24.28 vs 24.31 | No clear effect |
| use wavelet-domain features and FSS for rendering | WaveNeRF · DTU | HFIV: 0.103 -> 0.0521 | Improved |
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.
- GeoNeRF* — GeoNeRF: Generalizing NeRF With Geometry Priors (CVPR 2022) · better on 5 of 6 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
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.90)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 2024 · similarity 0.90)
- Few-Shot Neural Radiance Fields under Unconstrained Illumination (AAAI 2024 · similarity 0.90)
- ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field (AAAI 2024 · similarity 0.89)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.89)
- FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors (CVPR 2025 · similarity 0.89)
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.
