Research map / 3D vision / Depth and stereo
Towards Complete Scene and Regular Shape for Distortion Rectification by Curve-Aware Extrapolation
Kang Liao, Chunyu Lin, Yunchao Wei, Feng Li, Shangrong Yang, Yao Zhao
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 dilated residual connection (DRC) to the outpainting baseline (ablation) | ROP outpainting module · COCO-based rectified outpainting test | visual quality | Improved |
| add dual conditional expansion (DC) (ablation) | ROP outpainting module · COCO-based rectified outpainting test | visual quality | Improved |
| add curve-aware correlation measurement (CA) (ablation) | ROP outpainting module · COCO-based rectified outpainting test | visual quality | Improved |
| add curvature guidance to the rectification module (VGG16 and ResNet50) (ablation) | ROP rectification module · synthetic wide-angle test | distortion estimation error | Improved |
| add curvature guidance to the outpainting critic (ablation) | ROP outpainting module · COCO-based rectified outpainting test | content extrapolation error | Improved |
| ROP vs HiFill (best baseline), easy split | ROP vs HiFill · COCO-based rectified outpainting test (easy) | PSNR: 20.82 -> 23.40 | Improved |
| ROP vs HiFill, easy split FID | ROP vs HiFill · COCO-based rectified outpainting test (easy) | FID: 32.59 -> 21.48 | Improved |
| ROP vs HiFill, hard split | ROP vs HiFill · COCO-based rectified outpainting test (hard) | PSNR: 17.50 -> 19.41 | Improved |
| ROP vs RK, moderate split SSIM | ROP vs RK · COCO-based rectified outpainting test (moderate) | SSIM: 0.64 -> 0.71 | Improved |
Closest papers by meaning
- Wide-Angle Image Rectification: A Survey (IJCV 2022 · similarity 0.89)
- Lifting the Structural Morphing for Wide-Angle Images Rectification: Unified Content and Boundary Modeling (ICCV 2025 · similarity 0.89)
- Wide-Angle Rectification via Content-Aware Conformal Mapping (CVPR 2023 · similarity 0.89)
- RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning (ICCV 2023 · similarity 0.88)
- PRaDA: Projective Radial Distortion Averaging (CVPR 2025 · similarity 0.83)
- MaDCoW: Marginal Distortion Correction for Wide-Angle Photography with Arbitrary Objects (CVPR 2025 · 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.
