Research map / 3D vision / Depth and stereo
Light Field Reconstruction Using Deep Convolutional Network on EPI
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 the complete blur-restoration-deblur framework instead of CNN restoration alone (ablation) | EPI light field reconstruction · 30 scenes | PSNR: 37.15 -> 41.02 | Helped |
| Use the complete blur-restoration-deblur framework instead of CNN restoration alone (ablation) | EPI light field reconstruction · Reflective 29 | PSNR: 44.84 -> 46.10 | Helped |
| Use the complete blur-restoration-deblur framework instead of CNN restoration alone (ablation) | EPI light field reconstruction · Occlusion16 | PSNR: 35.89 -> 38.86 | Helped |
| Use residual learning rather than sparse coding for detail restoration (ablation) | EPI reconstruction framework · Buddha, 3 × 3 input | PSNR: 41.67 -> 43.20 | Helped |
| Use residual learning rather than sparse coding for detail restoration (ablation) | EPI reconstruction framework · Buddha, 5 × 5 input | PSNR: 41.79 -> 46.42 | Helped |
| Use residual learning rather than sparse coding for detail restoration (ablation) | EPI reconstruction framework · Mona, 3 × 3 input | PSNR: 42.39 -> 44.37 | Helped |
| Use residual learning rather than sparse coding for detail restoration (ablation) | EPI reconstruction framework · Mona, 5 × 5 input | PSNR: 44.40 -> 51.07 | Helped |
| Use residual learning rather than SRCNN for detail restoration (ablation) | EPI reconstruction framework · Buddha, 3 × 3 input | PSNR: 41.50 -> 43.20 | Helped |
| Use residual learning rather than SRCNN for detail restoration (ablation) | EPI reconstruction framework · Buddha, 5 × 5 input | PSNR: 42.45 -> 46.42 | Helped |
| Use residual learning rather than SRCNN for detail restoration (ablation) | EPI reconstruction framework · Mona, 3 × 3 input | PSNR: 42.64 -> 44.37 | Helped |
| Use residual learning rather than SRCNN for detail restoration (ablation) | EPI reconstruction framework · Mona, 5 × 5 input | PSNR: 43.86 -> 51.07 | Helped |
Closest papers by meaning
- Residual Networks for Light Field Image Super-Resolution (CVPR 2019 · similarity 0.91)
- EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth From Light Field Images (CVPR 2018 · similarity 0.90)
- Light Field Intrinsics With a Deep Encoder-Decoder Network (CVPR 2018 · similarity 0.89)
- Occlusion-Embedded Hybrid Transformer for Light Field Super-Resolution (AAAI 2025 · similarity 0.85)
- NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis (CVPR 2024 · similarity 0.84)
- From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy (NeurIPS 2025 · 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.