Perspective Fields for Single Image Camera Calibration
This work addresses camera calibration for applications requiring perspective understanding, offering a more interpretable and invariant approach, though it appears incremental as it builds on existing calibration concepts with a novel representation.
The paper tackles the problem of geometric camera calibration from a single image by introducing perspective fields, a representation modeling local perspective properties, and demonstrates its robustness in various scenarios compared to existing methods.
Geometric camera calibration is often required for applications that understand the perspective of the image. We propose perspective fields as a representation that models the local perspective properties of an image. Perspective Fields contain per-pixel information about the camera view, parameterized as an up vector and a latitude value. This representation has a number of advantages as it makes minimal assumptions about the camera model and is invariant or equivariant to common image editing operations like cropping, warping, and rotation. It is also more interpretable and aligned with human perception. We train a neural network to predict Perspective Fields and the predicted Perspective Fields can be converted to calibration parameters easily. We demonstrate the robustness of our approach under various scenarios compared with camera calibration-based methods and show example applications in image compositing.