CVFeb 6
A Unified Formula for Affine Transformations between Calibrated Cameras
arXiv:2602.06805v1h-index: 13
Originality Synthesis-oriented
AI Analysis
This provides a theoretical formula for computer vision tasks like image matching, but it is incremental as it builds on existing calibrated camera models.
The authors derived a closed-form expression for the affine transformation mapping local image patches between two calibrated camera views, showing it depends on relative camera pose, image coordinates, and local surface normal.
In this technical note, we derive a closed-form expression for the affine transformation mapping local image patches between two calibrated views. We show that the transformation is a function of the relative camera pose, the image coordinates, and the local surface normal.