Research map / 3D vision / NeRF and radiance fields
Geo-NI: Geometry-Aware Neural Interpolation for Light Field Rendering
Gaochang Wu, Yuemei Zhou, Lu Fang, Yebin Liu, Tianyou Chai
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 |
|---|---|---|---|
| add neural interpolation network instead of bilinear interpolation (ablation) | Geo-NI · MPI Light Field Archive (16x) | PSNR / SSIM: 36.50 -> 41.22 | Improved |
| add neural interpolation network instead of bilinear interpolation (ablation) | Geo-NI · MPI Light Field Archive (36x) | PSNR / SSIM: 32.72 -> 35.80 | Improved |
| add DIBR part to the NI network (ablation) | Geo-NI · MPI Light Field Archive (16x) | PSNR / SSIM: 41.03 -> 41.22 | Mixed |
| add DIBR part to the NI network (ablation) | Geo-NI · CIVIT Dataset (16x) | PSNR / SSIM: 44.62 -> 44.32 | Hurt |
| add DIBR part to the NI network (ablation) | Geo-NI · MPI Light Field Archive (36x) | PSNR / SSIM: 32.66 -> 35.80 | Improved |
| add DIBR part to the NI network (ablation) | Geo-NI · CIVIT Dataset (36x) | PSNR / SSIM: 38.98 -> 40.23 | Improved |
| add DIBR part to the NI network (ablation) | Geo-NI · Lytro 30 Scenes (7x) | PSNR / SSIM: 36.15 -> 40.68 | Improved |
| add DIBR part to the NI network (ablation) | Geo-NI · Lytro Occlusions (7x) | PSNR / SSIM: 32.12 -> 34.54 | Improved |
| use packing-unpacking structure instead of 3D U-net (ablation) | Geo-NI · MPI Light Field Archive (16x) | PSNR / SSIM: 39.90 -> 41.22 | Improved |
| use packing-unpacking structure instead of 3D U-net (ablation) | Geo-NI · MPI Light Field Archive (36x) | PSNR / SSIM: 33.01 -> 35.80 | Improved |
| use packing-unpacking structure instead of 3D U-net (ablation) | Geo-NI · CIVIT Dataset (36x) | PSNR / SSIM: 38.93 -> 40.23 | Improved |
| use packing-unpacking structure instead of 3D U-net (ablation) | Geo-NI · Lytro Reflective (7x) | PSNR / SSIM: 37.18 -> 38.05 | Improved |
Closest papers by meaning
- Light Field Neural Rendering (CVPR 2022 · similarity 0.92)
- Revisiting Light Field Rendering with Deep Anti-Aliasing Neural Network (TPAMI 2021 · similarity 0.91)
- Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering (NeurIPS 2021 · similarity 0.91)
- NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis (CVPR 2024 · similarity 0.88)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.88)
- GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis (CVPR 2025 · similarity 0.88)
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.
