FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification

TL;DR

This paper introduces FishEyeRecNet, a deep learning model that effectively rectifies fisheye images by learning high-level and low-level features simultaneously, outperforming existing methods on synthetic and real datasets.

Contribution

The paper presents a novel end-to-end multi-context deep network for fisheye image rectification, incorporating a synthesized dataset for training and evaluation.

Findings

Significantly outperforms current state-of-the-art methods

Effectively learns high-level semantics and low-level features

Generalizes well to real-world fisheye images

Abstract

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.