Research map / Image generation / Image restoration
Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flow
Shangrong Yang, Chunyu Lin, Kang Liao, Chunjie Zhang, Yao Zhao
Check 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 the flow estimation module (ablation) | PCN · Synthetic fisheye test | PSNR: 16.09 -> 24.98 | Improved |
| add the distortion correction module (ablation) | PCN · Synthetic fisheye test | PSNR: 19.12 -> 24.98 | Improved |
| add feature correction layers (ablation) | PCN · Synthetic fisheye test | PSNR: 21.31 -> 24.98 | Improved |
| add multi-scale loss and enhanced loss (ablation) | PCN · Synthetic fisheye test | PSNR: 23.26 -> 24.98 | Improved |
| add enhanced loss (ablation) | PCN · Synthetic fisheye test | PSNR: 23.69 -> 24.98 | Improved |
| correct layer 1 features with appearance flow (ablation) | PCN · Synthetic fisheye test | PSNR: 21.23 -> 24.98 | Improved |
| correct layer 3 features with appearance flow (ablation) | PCN · Synthetic fisheye test | PSNR: 22.95 -> 24.98 | Improved |
| correct layer 5 features with appearance flow (ablation) | PCN · Synthetic fisheye test | PSNR: 23.61 -> 24.98 | Improved |
| correct layers 1 and 2 features with appearance flow (ablation) | PCN · Synthetic fisheye test | PSNR: 21.20 -> 24.98 | Improved |
| correct layers 4 and 5 features with appearance flow (ablation) | PCN · Synthetic fisheye test | PSNR: 23.16 -> 24.98 | Improved |
| correct layers 1, 2, and 3 features with appearance flow (ablation) | PCN · Synthetic fisheye test | PSNR: 19.64 -> 24.98 | Improved |
| correct layers 3, 4, and 5 features with appearance flow (ablation) | PCN · Synthetic fisheye test | PSNR: 22.63 -> 24.98 | Improved |
Closest papers by meaning
- SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning (ICCV 2023 · similarity 0.90)
- QueryCDR: Query-based Controllable Distortion Rectification Network for Fisheye Images (ECCV 2024 · similarity 0.90)
- FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification (ECCV 2018 · similarity 0.89)
- Learning to Calibrate Straight Lines for Fisheye Image Rectification (CVPR 2019 · similarity 0.88)
- Innovating Real Fisheye Image Correction with Dual Diffusion Architecture (ICCV 2023 · similarity 0.87)
- Spatiotemporal Deformation Perception for Fisheye Video Rectification (AAAI 2023 · similarity 0.86)
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.
