Research map / Image generation / Super-resolution
Residual Networks for Light Field Image Super-Resolution
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 |
|---|---|---|---|
| Combine image stacks from multiple angular directions rather than only horizontal or vertical stacks (ablation) | resLF · ×2 SR test dataset | average PSNR: 36.27 -> 37.77; 36.32 -> 37.77 | Helped |
| Add diagonal-direction stacks to horizontal and vertical stacks (ablation) | resLF · ×2 SR test dataset | average PSNR: 37.35 -> 37.77 | Helped |
| Use more angular views in the image stacks (ablation) | resLF · ×2 SR test dataset | average PSNR: 37.24 -> 37.60 -> 37.65 -> 37.77 | Helped |
| Use incomplete 3×2 rather than full 3×3 image stacks (ablation) | resLF · ×2 SR test dataset | average PSNR: 37.77 -> 37.19 | Hurt |
| Use incomplete 2×3 rather than full 3×3 image stacks (ablation) | resLF · ×2 SR test dataset | average PSNR: 37.77 -> 37.09 | Hurt |
| Use incomplete 2×2 rather than full 3×3 image stacks (ablation) | resLF · ×2 SR test dataset | average PSNR: 37.77 -> 37.02 | Hurt |
| Use H3×3 rather than H9×9 angular resolution (ablation) | resLF · ×2 SR test dataset | average PSNR: 37.77 -> 37.24 | Hurt |
| Use the proposed multi-directional resLF method instead of EDSR | ×2 LF super-resolution · HCI1 | PSNR: 39.24 -> 41.09 | Helped |
| Use the proposed multi-directional resLF method instead of EDSR | ×2 LF super-resolution · Occlusions | PSNR: 37.61 -> 39.71 | Helped |
| Use the proposed multi-directional resLF method instead of EDSR | ×4 LF super-resolution · ISO Chart 12 | PSNR: 30.96 -> 32.57 | Helped |
Closest papers by meaning
- Learning Light Field Angular Super-Resolution via a Geometry-Aware Network (AAAI 2020 · similarity 0.92)
- High-Order Residual Network for Light Field Super-Resolution (AAAI 2020 · similarity 0.91)
- Light Field Reconstruction Using Deep Convolutional Network on EPI (CVPR 2017 · similarity 0.91)
- Detail-Preserving Transformer for Light Field Image Super-resolution (AAAI 2022 · similarity 0.89)
- Occlusion-Embedded Hybrid Transformer for Light Field Super-Resolution (AAAI 2025 · similarity 0.86)
- ResFields: Residual Neural Fields for Spatiotemporal Signals (ICLR 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.