Learning to Calibrate Straight Lines for Fisheye Image Rectification
This work addresses fisheye image rectification for computer vision applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of calibrating fisheye lens parameters and rectifying distorted images by introducing a deep neural network that enforces geometry constraints and uses multi-scale perception. It achieves the best published rectification quality and most accurate distortion parameter estimation on synthetic and real images.
This paper presents a new deep-learning based method to simultaneously calibrate the intrinsic parameters of fisheye lens and rectify the distorted images. Assuming that the distorted lines generated by fisheye projection should be straight after rectification, we propose a novel deep neural network to impose explicit geometry constraints onto processes of the fisheye lens calibration and the distorted image rectification. In addition, considering the nonlinearity of distortion distribution in fisheye images, the proposed network fully exploits multi-scale perception to equalize the rectification effects on the whole image. To train and evaluate the proposed model, we also create a new largescale dataset labeled with corresponding distortion parameters and well-annotated distorted lines. Compared with the state-of-the-art methods, our model achieves the best published rectification quality and the most accurate estimation of distortion parameters on a large set of synthetic and real fisheye images.