Research map / 3D vision / NeRF and radiance fields
PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas
Zheng Chen, Yan-Pei Cao, Yuan-Chen Guo, Chen Wang, Ying Shan, Song-Hai 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 |
|---|---|---|---|
| zero out appearance feature (ablation) | PanoGRF · Matterport3D 1.0m | PSNR: 28.10 -> 5.44 | Hurt |
| zero out geometry feature (ablation) | PanoGRF · Matterport3D 1.0m | PSNR: 28.10 -> 26.25 | Hurt |
| add mono depth to MVS depth estimator (resnet-18) (ablation) | MVS · Matterport3D | L1: 0.1731 -> 0.1441 | Improved |
| larger ResNet backbone for MVS+Mono (ablation) | MVS+Mono · Matterport3D | L1: 0.1441 -> 0.1735 | Hurt |
| more MVS ResNet depth (18 to 50) without mono (ablation) | MVS · Matterport3D | L1: 0.1731 -> 0.1598 | Improved |
| number of mono depth candidates N_mono 1 to 5 (ablation) | depth sampling · Matterport3D | WS-L1: 0.1745 -> 0.1502 | Improved |
| N_mono from 5 to 9 (ablation) | depth sampling · Matterport3D | WS-L1: 0.1502 -> 0.1752 | Hurt |
| sigma 0.5 to 1.0 (ablation) | mono-guided sampling · Matterport3D | WS-L1: 0.1502 -> 0.1803 | Hurt |
| PanoGRF vs Cross Attention Renderer | PanoGRF · Matterport3D 1.0m | PSNR: 22.87 -> 27.78 | Improved |
| PanoGRF vs NeuRay with multi-view inputs | PanoGRF · Matterport3D 1.0m | PSNR: 27.82 -> 28.99 | Improved |
| PanoGRF vs NeuRay* | PanoGRF · Replica 1.0m | PSNR: 26.62 -> 30.08 | Improved |
Later papers that compared with this method
1 later accepted paper reports PanoGRF as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting (CVPR 2025 · better on 2 of 4 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
- Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images (CVPR 2025 · similarity 0.89)
- Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images (AAAI 2024 · similarity 0.87)
- MuRF: Multi-Baseline Radiance Fields (CVPR 2024 · similarity 0.87)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 2024 · similarity 0.87)
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · similarity 0.86)
- PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting (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.
