CTRL-C: Camera calibration TRansformer with Line-Classification
This work addresses camera calibration for computer vision applications, offering a novel method that improves accuracy on standard benchmarks.
The paper tackles single image camera calibration by proposing CTRL-C, an end-to-end transformer-based network that estimates camera parameters from an image and line segments, outperforming previous state-of-the-art methods on Google Street View and SUN360 datasets.
Single image camera calibration is the task of estimating the camera parameters from a single input image, such as the vanishing points, focal length, and horizon line. In this work, we propose Camera calibration TRansformer with Line-Classification (CTRL-C), an end-to-end neural network-based approach to single image camera calibration, which directly estimates the camera parameters from an image and a set of line segments. Our network adopts the transformer architecture to capture the global structure of an image with multi-modal inputs in an end-to-end manner. We also propose an auxiliary task of line classification to train the network to extract the global geometric information from lines effectively. Our experiments demonstrate that CTRL-C outperforms the previous state-of-the-art methods on the Google Street View and SUN360 benchmark datasets.