SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation
This work addresses the problem of robust homography estimation for computer vision applications, but it is incremental as it builds on traditional pipeline steps with deep learning enhancements.
The paper tackles robust homography estimation by proposing a deep learning model that mimics all four steps of the traditional pipeline, including feature matching and outlier removal, and demonstrates that it outperforms existing deep learning models on synthetic and real datasets.
The traditional homography estimation pipeline consists of four main steps: feature detection, feature matching, outlier removal and transformation estimation. Recent deep learning models intend to address the homography estimation problem using a single convolutional network. While these models are trained in an end-to-end fashion to simplify the homography estimation problem, they lack the feature matching step and/or the outlier removal step, which are important steps in the traditional homography estimation pipeline. In this paper, we attempt to build a deep learning model that mimics all four steps in the traditional homography estimation pipeline. In particular, the feature matching step is implemented using the cost volume technique. To remove outliers in the cost volume, we treat this outlier removal problem as a denoising problem and propose a novel self-supervised loss to solve the problem. Extensive experiments on synthetic and real datasets demonstrate that the proposed model outperforms existing deep learning models.