Research map / 3D vision / Depth and stereo
Light Field Neural Rendering
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 |
|---|---|---|---|
| add epipolar geometric constraints and two-stage transformer aggregation instead of direct light-field MLP prediction (ablation) | Light Field Neural Rendering · RFF (25% resolution) | PSNR: 17.39 -> 28.78 | Helped |
| use separate epipolar and view transformers rather than one MLP (ablation) | Light Field Neural Rendering · RFF (25% resolution) | PSNR: 21.33 -> 28.78 | Helped |
| use transformers instead of MLPs for epipolar and view aggregation (ablation) | Light Field Neural Rendering · RFF (25% resolution) | PSNR: 26.16 -> 28.78 | Helped |
| add CNN visual features at epipolar points (ablation) | Light Field Neural Rendering · RFF (25% resolution) | PSNR: 27.43 -> 28.78 | Helped |
| include 3D point coordinates in epipolar features (ablation) | Light Field Neural Rendering · RFF (25% resolution) | PSNR: 28.17 -> 28.78 | Helped |
| add learnable camera embeddings (ablation) | Light Field Neural Rendering · RFF (25% resolution) | PSNR: 28.23 -> 28.78 | Helped |
| use attention-based aggregation instead of mean pooling (ablation) | Light Field Neural Rendering · RFF (25% resolution) | PSNR: 28.39 -> 28.78 | Helped |
| add the auxiliary color loss (ablation) | Light Field Neural Rendering · RFF (25% resolution) | PSNR: 28.43 -> 28.78 | Helped |
| use light-field ray fusion with epipolar geometric constraints and transformer aggregation | Light Field Neural Rendering · RFF | PSNR [dB]: 27.26 -> 28.26 | Helped |
| use light-field ray fusion with epipolar geometric constraints and transformer aggregation | Light Field Neural Rendering · Shiny | PSNR: 26.50 -> 27.34 | Helped |
| use light-field ray fusion with epipolar geometric constraints and transformer aggregation | Light Field Neural Rendering · Blender | PSNR: 33.09 -> 33.85 | Helped |
Closest papers by meaning
- Learning Neural Light Fields With Ray-Space Embedding (CVPR 2022 · similarity 0.93)
- NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis (CVPR 2024 · similarity 0.89)
- GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis (CVPR 2025 · similarity 0.89)
- SpecNeRF: Gaussian Directional Encoding for Specular Reflections (CVPR 2024 · similarity 0.89)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.89)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · 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.