Research map / 3D vision / NeRF and radiance fields
Few-shot NeRF by Adaptive Rendering Loss Regularization
Qingshan Xu, Xuanyu Yi, Jianyao Xu, Wenbing Tao, Yew Soon Ong, Hanwang Zhang
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 two-phase rendering supervision (blurred early supervision) (ablation) | FreeNeRF baseline · DTU 3 views | PSNR: 19.54 -> 19.81 | Improved |
| add adaptive rendering loss weight learning (ablation) | FreeNeRF baseline · DTU 3 views | PSNR: 19.54 -> 19.73 | Improved |
| combine two-phase supervision and adaptive weight learning (ablation) | FreeNeRF baseline · DTU 3 views | PSNR: 19.54 -> 20.01 | Improved |
| add ray density regularization (ablation) | Model-C · DTU 3 views | PSNR: 20.01 -> 20.07 | Improved |
| use learned adaptive loss instead of linear weighting (ablation) | AR-NeRF · DTU 3 views | PSNR: 19.66 -> 20.01 | Improved |
| use ray density regularization instead of Emptiness loss (ablation) | AR-NeRF (Model-C) · DTU 3 views | PSNR: 19.33 -> 20.07 | Improved |
| reduce high-frequency pixel supervision when only low-frequency PEs are enabled (ablation) | NeRF with 10% PEs · DTU 3 views, low-frequency pixels | PSNR | Improved |
| apply AR-NeRF versus FreeNeRF with 6 and 9 input views | AR-NeRF · DTU 6/9 views | PSNR: 23.14 -> 23.17 (6-view); 25.60 -> 25.62 (9-view) | No clear effect |
| apply AR-NeRF versus FreeNeRF with 3 input views | AR-NeRF · LLFF 3 views | PSNR: 19.63 -> 19.90 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FreeNeRF — FreeNeRF: Improving Few-Shot Neural Rendering With Free Frequency Regularization (CVPR 2023) · better on 6 of 7 shared results
- MixNeRF — MixNeRF: Modeling a Ray With Mixture Density for Novel View Synthesis From Sparse Inputs (CVPR 2023) · better on 1 of 1 shared result
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
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.90)
- Spatial Annealing for Efficient Few-shot Neural Rendering (AAAI 2025 · similarity 0.90)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.90)
- FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors (CVPR 2025 · similarity 0.89)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.89)
- CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis (AAAI 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.
