Research map / 3D vision / NeRF and radiance fields
Balanced Spherical Grid for Egocentric View Synthesis
Changwoon Choi, Sang Min Kim, Young Min Kim
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 |
|---|---|---|---|
| Use a balanced spherical feature grid instead of Cartesian feature grids | EgoNeRF · OmniBlender and Ricoh360 | PSNR | Improved |
| Add an exponentially partitioned radial grid (ablation) | EgoNeRF · OmniBlender Indoor | PSNR: 31.32 -> 33.11 | Improved |
| Add an exponentially partitioned radial grid (ablation) | EgoNeRF · OmniBlender Outdoor | PSNR: 26.66 -> 30.56 | Improved |
| Add the Yin-Yang angular grid (ablation) | EgoNeRF · OmniBlender Indoor | PSNR: 30.53 -> 33.11 | Improved |
| Add the Yin-Yang angular grid (ablation) | EgoNeRF · OmniBlender Outdoor | PSNR: 26.74 -> 30.56 | Improved |
| Use a balanced spherical grid instead of a regular spherical grid (ablation) | EgoNeRF · OmniBlender Indoor | PSNR: 30.78 -> 33.11 | Improved |
| Use a balanced spherical grid instead of a regular spherical grid (ablation) | EgoNeRF · OmniBlender Outdoor | PSNR: 26.25 -> 30.56 | Improved |
| Add resampling rather than removing it and doubling ray samples (ablation) | EgoNeRF · OmniBlender Indoor | PSNR: 32.40 -> 33.11 | Improved |
| Add resampling rather than removing it and doubling ray samples (ablation) | EgoNeRF · OmniBlender Outdoor | PSNR: 30.12 -> 30.56 | Improved |
| Add an environment map (ablation) | EgoNeRF · OmniBlender Outdoor | PSNR: 30.04 -> 30.56 | Improved |
| Use fine-resolution feature grids under camera-pose noise | EgoNeRF · OmniBlender BarberShop with pose noise | PSNR | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- mip-NeRF 360 — Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields (CVPR 2022) · better on 1 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
- HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces (CVPR 2024 · similarity 0.87)
- Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation (NeurIPS 2026 · similarity 0.86)
- Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views (AAAI 2024 · similarity 0.86)
- NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods (NeurIPS 2025 · similarity 0.85)
- PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting (CVPR 2025 · similarity 0.84)
- Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency (CVPR 2024 · similarity 0.84)
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.
