Research map / 3D vision / NeRF and radiance fields
General Neural Gauge Fields
Fangneng Zhan, Lingjie Liu, Adam Kortylewski, Christian Theobalt
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 |
|---|---|---|---|
| learn a continuous 3D-to-2D gauge with InfoReg instead of orthogonal mapping | Neural Gauge Fields · S-NeRF, S-NSVF, DTU, T&T | PSNR: 18.20 -> 30.74; 19.32 -> 32.51; 23.31 -> 27.06; 19.97 -> 25.95 | Improved |
| replace the spatial hash function with learned top-1 discrete gauge mapping | Neural Gauge Fields · S-NeRF, S-NSVF, DTU, T&T | PSNR: 27.06 -> 26.56; 29.81 -> 29.13; 27.02 -> 26.21; 26.22 -> 24.79 | Hurt |
| use top-4 instead of top-1 selection for learned discrete gauge mapping (ablation) | Learning Discrete Gauge · S-NeRF, S-NSVF, DTU, T&T | PSNR: 26.56 -> 29.39; 29.13 -> 31.39; 26.21 -> 28.77; 24.79 -> 27.14 | Improved |
| add top-4 learned discrete mapping rather than use the spatial hash function | Neural Gauge Fields · S-NeRF, S-NSVF, DTU, T&T | PSNR: 27.06 -> 29.39; 29.81 -> 31.39; 27.02 -> 28.77; 26.22 -> 27.14 | Improved |
| add InfoInv | NeRF · Synthetic-NeRF | PSNR: 31.01 -> 31.55 | Improved |
| add InfoInv | NeRF · Synthetic-NeRF | SSIM: 0.947 -> 0.953 | Improved |
| add InfoInv | NeuS · DTU | PSNR: 31.97 -> 32.24 | Improved |
| add InfoInv | NeuS · DTU | Chamfer: 0.84 -> 0.80 | Improved |
| add InfoInv | TriPlane (Radiance) · Synthetic-NeRF | PSNR: 31.47 -> 31.76 | Improved |
| add InfoInv | TriPlane (Radiance) · Synthetic-NeRF | SSIM: 0.951 -> 0.956 | Improved |
| add InfoInv | TriPlane (SDF) · DTU | PSNR: 32.51 -> 32.75 | Improved |
| add InfoInv | TriPlane (SDF) · DTU | Chamfer: 0.76 -> 0.73 | 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.
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 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
- 3D Reconstruction with Generalizable Neural Fields using Scene Priors (ICLR 2024 · similarity 0.84)
- Neural Isometries: Taming Transformations for Equivariant ML (NeurIPS 2024 · similarity 0.84)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 2024 · similarity 0.83)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 2024 · similarity 0.83)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.83)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.83)
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.
