Research map / Image generation / Image restoration
A Perceptual Measure for Deep Single Image Camera and Lens Calibration
Yannick Hold-Geoffroy, Dominique Piché‐Meunier, Kalyan Sunkavalli, Jean‐Charles Bazin, François Rameau, Jean‐François Lalonde
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 |
|---|---|---|---|
| compare single-image network to multi-image checkerboard calibration (Mei) | deep single-image calibration · Avenir 2.8mm reprojection error | reprojection error: 0.12 vs 0.64 | Hurt |
| compare single-image network to Zhang (Brown model) | deep single-image calibration · Avenir 4mm reprojection error | reprojection error: 0.29 vs 0.57 | Hurt |
| compare single-image network to Scaramuzza toolbox | deep single-image calibration · Avenir 4mm reprojection error | reprojection error: 0.54 -> 0.57 is not better; Scaramuzza 1.01 vs Ours 0.64 on Avenir 2.8mm | Improved |
| compare single-image network to Fitzgibbon division model on GoPro | deep single-image calibration · GoPro reprojection error | reprojection error: 0.7 vs 2.74 | Hurt |
| scene type: nature instead of artificial or urban | human observers · distortion sensitivity | accuracy: 75% / 74% -> 43% | Hurt |
| insert object at exact image center | human observers · distortion sensitivity | accuracy: accuracy falls to nearly 50% | Hurt |
| train network with the perceptual measure as loss (ablation) | deep calibration network · calibration accuracy | error | No clear effect |
Closest papers by meaning
- A Perceptual Measure for Deep Single Image Camera Calibration (CVPR 2018 · similarity 0.96)
- Perspective Fields for Single Image Camera Calibration (CVPR 2023 · similarity 0.87)
- Deep Geometry-Aware Camera Self-Calibration from Video (ICCV 2023 · similarity 0.87)
- Why Having 10,000 Parameters in Your Camera Model Is Better Than Twelve (CVPR 2020 · similarity 0.86)
- AlignDiff: Learning Physically-Grounded Camera Alignment via Diffusion (ICCV 2025 · similarity 0.85)
- Inferring Bias and Uncertainty in Camera Calibration (IJCV 2021 · 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.
