FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification
This addresses the need for accurate fisheye image rectification as a preprocessing step in computer vision, but it is incremental as it builds on existing deep learning approaches for distortion removal.
The paper tackles the problem of rectifying distortions in fisheye images, which is crucial for computer vision applications, by proposing an end-to-end multi-context collaborative deep network that learns high-level semantics and low-level appearance features to estimate distortion parameters, and it significantly outperforms current state-of-the-art methods on both synthesized and real-world datasets.
Images captured by fisheye lenses violate the pinhole camera assumption and suffer from distortions. Rectification of fisheye images is therefore a crucial preprocessing step for many computer vision applications. In this paper, we propose an end-to-end multi-context collaborative deep network for removing distortions from single fisheye images. In contrast to conventional approaches, which focus on extracting hand-crafted features from input images, our method learns high-level semantics and low-level appearance features simultaneously to estimate the distortion parameters. To facilitate training, we construct a synthesized dataset that covers various scenes and distortion parameter settings. Experiments on both synthesized and real-world datasets show that the proposed model significantly outperforms current state of the art methods. Our code and synthesized dataset will be made publicly available.