Supervised Homography Learning with Realistic Dataset Generation

TL;DR

This paper introduces an iterative framework for generating realistic training data and training a supervised homography network, leading to improved performance and state-of-the-art results in homography estimation.

Contribution

The proposed method combines data generation and network training in an iterative process to enhance dataset realism and network accuracy for homography estimation.

Findings

Achieves state-of-the-art performance in homography estimation

Improves existing supervised methods using generated datasets

Demonstrates the effectiveness of iterative data refinement

Abstract

In this paper, we propose an iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised homography network. In the generation phase, given an unlabeled image pair, we utilize the pre-estimated dominant plane masks and homography of the pair, along with another sampled homography that serves as ground truth to generate a new labeled training pair with realistic motion. In the training phase, the generated data is used to train the supervised homography network, in which the training data is refined via a content consistency module and a quality assessment module. Once an iteration is finished, the trained network is used in the next data generation phase to update the pre-estimated homography. Through such an iterative strategy, the quality of the dataset and the performance of the network can be gradually and simultaneously improved. Experimental results show that our method achieves state-of-the-art performance and existing supervised methods can be also improved based on the generated dataset. Code and dataset are available at https://github.com/JianghaiSCU/RealSH.