SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation

TL;DR

This paper introduces SSORN, a deep learning model that mimics traditional homography estimation steps, including feature matching and outlier removal, using self-supervised learning to improve robustness and accuracy.

Contribution

The paper presents a novel self-supervised outlier removal network that integrates all traditional homography steps into a deep learning framework, enhancing performance.

Findings

Outperforms existing deep learning models on synthetic datasets

Effective outlier removal via self-supervised denoising

Accurate homography estimation on real datasets

Abstract

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.