Research map / 3D vision / Depth and stereo
Revisiting Calibration of Wide-Angle Radially Symmetric Cameras
Andrea Porfiri Dal Cin, Francesco Azzoni, Giacomo Boracchi, Luca Magri
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 |
|---|---|---|---|
| remove polar features and use Cartesian features only (C=0) (ablation) | VaCR network · KITTI-360 rectification | SSIM/PSNR: 0.610/17.53 -> 0.289/10.61 | Hurt |
| increase Cartesian channels D beyond 96 (ablation) | VaCR network · KITTI-360 rectification | SSIM/PSNR: 0.610/17.53 -> 0.611/17.55 (D=192) | No clear effect |
| increase polar channels C with D fixed (ablation) | VaCR network · KITTI-360 rectification | SSIM/PSNR: 0.571/16.00 (C=192) -> 0.610/17.53 (C=384) | Improved |
| decouple camera model from network via VaCR and robust fitting, using DSCM or EUCM | calibration framework · Calibration Re across four datasets | reprojection error: Re 4.015 (DSCM) vs 7.882 (Wakai) on KITTI-360 | Improved |
| use UCM model within the two-step framework instead of DeepCalib end-to-end regression | calibration framework · KITTI-360 | reprojection error: 21.936 -> 5.272 | Improved |
| use two-step VaCR with KB3 versus Wakai end-to-end | calibration framework · KITTI-360 | reprojection error: 7.882 -> 5.324 | Improved |
| add robust fitting step instead of direct parameter regression | calibration framework · Running speed | FPS: Wakai up to 13% faster | Hurt |
Closest papers by meaning
- Self-Calibrating Neural Radiance Fields (ICCV 2021 · similarity 0.89)
- Deep Single Image Camera Calibration With Radial Distortion (CVPR 2019 · similarity 0.87)
- Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning (ECCV 2026 · similarity 0.86)
- Wide-Angle Image Rectification: A Survey (IJCV 2022 · similarity 0.86)
- PRaDA: Projective Radial Distortion Averaging (CVPR 2025 · similarity 0.85)
- CRAYM: Neural Field Optimization via Camera RAY Matching (NeurIPS 2024 · similarity 0.85)
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.
