Research map / Image generation / Image restoration
CTRL-C: Camera Calibration TRansformer With Line-Classification
Jinwoo Lee, Hyunsung Go, Hyunjoon Lee, Sunghyun Cho, Minhyuk Sung, Junho Kim
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 transformer encoder-decoder on top of ResNet (ablation) | ResNet regressor · Google Street View test | Horizon AUC (%): 84.48 -> 85.65 | Improved |
| add transformer encoder-decoder on top of ResNet (ablation) | ResNet regressor · SUN360 test | Horizon AUC (%): 83.94 -> 84.39 | Improved |
| add line input and vertical convergence line classification (ablation) | CTRL-C transformer · Google Street View test | Horizon AUC (%): 85.65 -> 87.16 | Improved |
| add line input and vertical convergence line classification (ablation) | CTRL-C transformer · SUN360 test | Horizon AUC (%): 84.39 -> 85.09 | Improved |
| add line input and horizontal convergence line classification (ablation) | CTRL-C transformer · Google Street View test | Horizon AUC (%): 85.65 -> 86.09 | Improved |
| add line input and horizontal convergence line classification (ablation) | CTRL-C transformer · SUN360 test | Horizon AUC (%): 84.39 -> 85.36 | Improved |
| add horizontal classification on top of vertical classification (ablation) | CTRL-C · Google Street View test | Horizon AUC (%): 87.16 -> 87.29 | Improved |
| add horizontal classification on top of vertical classification (ablation) | CTRL-C · SUN360 test | Horizon AUC (%): 85.09 -> 85.45 | Improved |
| add horizontal classification on top of vertical classification (ablation) | CTRL-C · SUN360 test | FoV mean error (deg): 3.76 -> 3.80 | No clear effect |
| add more transformer decoder layers (1 to 6) | CTRL-C · Google Street View test | Horizon AUC (%): 86.46 -> 87.29 | Improved |
| add more transformer decoder layers (1 to 6) | CTRL-C · Google Street View test | Up direction mean error (deg): 2.34 -> 1.80 | Improved |
| replace GPNet with CTRL-C | GPNet · Google Street View test | Horizon AUC (%): 83.12 -> 87.29 | Improved |
Closest papers by meaning
- Neural Geometric Parser for Single Image Camera Calibration (ECCV 2020 · similarity 0.87)
- A Perceptual Measure for Deep Single Image Camera Calibration (CVPR 2018 · similarity 0.85)
- Deep Single Image Camera Calibration With Radial Distortion (CVPR 2019 · similarity 0.84)
- GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024 · similarity 0.84)
- Camera Resection from Known Line Pencils and a Radially Distorted Scanline (CVPR 2025 · similarity 0.82)
- ViT-Calibrator: Decision Stream Calibration for Vision Transformer (AAAI 2024 · similarity 0.82)
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.
