Research map / 3D vision / NeRF and radiance fields
InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering
Mijeong Kim, Seonguk Seo, Bohyung Han
Check 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 ray entropy minimization and ray information gain reduction to NeRF | NeRF · Realistic Synthetic 360° (4-view) | PSNR: 16.06 -> 18.65 | Improved |
| add ray entropy minimization and ray information gain reduction to NeRF | NeRF · ZJU-MoCap (4-view) | PSNR: 21.74 -> 22.88 | Improved |
| add ray entropy minimization and ray information gain reduction to NeRF | NeRF · DTU (3-view) | PSNR: 8.50 -> 11.23 | Improved |
| add ray entropy minimization and ray information gain reduction to NeRF | NeRF · LLFF (2-view) | PSNR: 12.93 -> 14.37 | Improved |
| add 1,024 unseen-view rays rather than none (ablation) | InfoNeRF · Realistic Synthetic 360° Chair (4-view) | PSNR: 20.14 -> 21.37 | Improved |
| add ray entropy minimization (ablation) | InfoNeRF without entropy loss · DTU (3-view) | PSNR: 8.91 -> 11.23 | Improved |
| add ray entropy minimization (ablation) | InfoNeRF without entropy loss · DTU (3-view) | SSIM: 0.439 -> 0.445 | Improved |
| add ray information gain reduction (ablation) | InfoNeRF without KL loss · DTU (3-view) | PSNR: 10.54 -> 11.23 | Improved |
| add ray information gain reduction (ablation) | InfoNeRF without KL loss · DTU (3-view) | SSIM: 0.418 -> 0.445 | Improved |
| add ray information gain reduction alongside entropy minimization (ablation) | InfoNeRF · Realistic Synthetic 360° Lego, narrow baseline (4-view) | PSNR: 16.74 -> 18.41 | Improved |
| add ray information gain reduction alongside entropy minimization (ablation) | InfoNeRF · Realistic Synthetic 360° Lego, wide baseline (4-view) | PSNR: 19.51 -> 19.28 | Hurt |
| add ray information gain reduction without entropy minimization (ablation) | InfoNeRF · Realistic Synthetic 360° Lego (4-view) | PSNR: 13.16 -> 13.33; 18.03 -> 17.96 | Mixed |
Later papers that compared with this method
5 later accepted papers report InfoNeRF as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Global and Hierarchical Geometry Consistency Priors for Few-shot NeRFs in Indoor Scenes (CVPR 2024 · better on 1 of 1 shared result)
- ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining (CVPR 2024 · better on 1 of 1 shared result)
- MixNeRF: Modeling a Ray With Mixture Density for Novel View Synthesis From Sparse Inputs (CVPR 2023 · better on 3 of 3 shared results)
- GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency (ICML 2023 · better on 3 of 3 shared results)
- Novel-View Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views (ICCV 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
- Ray Priors Through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation (CVPR 2022 · similarity 0.87)
- Spatial Annealing for Efficient Few-shot Neural Rendering (AAAI 2025 · similarity 0.85)
- GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis (CVPR 2025 · similarity 0.85)
- HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces (CVPR 2024 · similarity 0.85)
- HashPoint: Accelerated Point Searching and Sampling for Neural Rendering (CVPR 2024 · similarity 0.85)
- Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion (CVPR 2025 · similarity 0.85)
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.
