Research map / 3D vision / NeRF and radiance fields
GeoNeRF: Generalizing NeRF With Geometry Priors
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 GeoNeRF's geometry priors, cascaded cost volumes, and occlusion-aware attention instead of MVSNeRF | Generalizable novel-view synthesis · DTU MVS | PSNR: 26.63 -> 31.34 | Helped |
| Use GeoNeRF's geometry priors, cascaded cost volumes, and occlusion-aware attention instead of IBRNet | Generalizable novel-view synthesis · Realistic Synthetic | PSNR: 25.49 -> 28.33 | Helped |
| Use GeoNeRF's geometry priors, cascaded cost volumes, and occlusion-aware attention instead of IBRNet | Generalizable novel-view synthesis · Real Forward Facing | PSNR: 25.13 -> 25.44 | Helped |
| Increase source views from 3 to 9 (ablation) | GeoNeRF · LLFF test scenes | PSNR: 24.33 -> 25.44 | Helped |
| Increase source views from 3 to 9 (ablation) | GeoNeRF · LLFF test scenes | LPIPS: 0.212 -> 0.180 | Mixed |
| Discard the 2 nearest source views (ablation) | GeoNeRF · LLFF test scenes | PSNR: 25.44 -> 24.18 | Hurt |
| Add incomplete, low-resolution depth input (ablation) | GeoNeRF · DTU MVS test scenes | PSNR: 31.34 -> 31.58 | Helped |
| Add incomplete, low-resolution depth input (ablation) | GeoNeRF · DTU MVS test scenes | LPIPS: 0.060 -> 0.057 | Helped |
Closest papers by meaning
- GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding (CVPR 2024 · similarity 0.91)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 2024 · similarity 0.89)
- HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces (CVPR 2024 · similarity 0.89)
- ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field (AAAI 2024 · similarity 0.88)
- GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis (CVPR 2025 · similarity 0.87)
- AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization (AAAI 2024 · similarity 0.87)
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.