Research map / Image generation / Super-resolution
Spatial-Angular Interaction for Light Field Image Super-Resolution
Yingqian Wang, Longguang Wang, Jungang Yang, Wei An, Jingyi Yu, Yulan Guo
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 angular information path (ablation) | LF-InterNet · STFlytro 4xSR | PSNR: 29.98 -> 31.65 | Improved |
| add spatial 3x3 convolution information (ablation) | LF-InterNet · STFlytro 4xSR | PSNR: 26.57 -> 31.65 | Improved |
| decouple spatial and angular features (vs coupled, same size) (ablation) | LF-InterNet · STFlytro 4xSR | PSNR: 31.11 -> 31.65 | Improved |
| decouple spatial and angular features (vs coupled, same FLOPs) (ablation) | LF-InterNet · STFlytro 4xSR | PSNR: 31.17 -> 31.65 | Improved |
| add first spatial-angular interaction group (ablation) | LF-InterNet · STFlytro 4xSR | PSNR: 29.84 -> 31.44 | Improved |
| increase interaction groups from 1 to 4 (ablation) | LF-InterNet · STFlytro 4xSR | PSNR: 31.44 -> 31.84 | Improved |
| use pixel shuffling instead of bilinear upsampling (ablation) | LF-InterNet · STFlytro 4xSR | PSNR: 30.71 -> 31.84 | Improved |
| use pixel shuffling instead of nearest upsampling (ablation) | LF-InterNet · STFlytro 4xSR | PSNR: 31.65 -> 31.84 | Improved |
| increase angular resolution from 3x3 to 9x9 (ablation) | LF-InterNet · STFlytro 4xSR | PSNR: 31.30 -> 32.07 | Improved |
| increase angular resolution from 7x7 to 9x9 (ablation) | LF-InterNet · STFlytro 2xSR | PSNR: 39.05 -> 39.08 | No clear effect |
| double feature depth from 32 to 64 | LF-InterNet · LF SR 4x average of 6 datasets | PSNR: 31.57 -> 31.95 | Improved |
| use LF-InterNet instead of LF-ATO | LF-ATO · UCSD unseen 2xSR | PSNR: 41.80 -> 42.36 | Improved |
Closest papers by meaning
- Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution (ICCV 2023 · similarity 0.90)
- Learning Light Field Angular Super-Resolution via a Geometry-Aware Network (AAAI 2020 · similarity 0.89)
- Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization (CVPR 2020 · similarity 0.89)
- Occlusion-Embedded Hybrid Transformer for Light Field Super-Resolution (AAAI 2025 · similarity 0.85)
- Event Fields: Capturing Light Fields at High Speed, Resolution, and Dynamic Range (CVPR 2025 · similarity 0.84)
- Time-Efficient Light-Field Acquisition Using Coded Aperture and Events (CVPR 2024 · similarity 0.83)
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.
