Learning Stereo from Single Images

TL;DR

This paper introduces a method to generate stereo training data from single images using monocular depth estimation, reducing the need for ground truth stereo data and enabling training on diverse datasets like COCO.

Contribution

It presents a novel pipeline that creates stereo training pairs from single images, allowing effective stereo network training without relying on real or synthetic stereo data.

Findings

Outperforms traditional stereo training methods on KITTI, ETH3D, Middlebury datasets.

Enables training on diverse datasets like COCO for stereo matching.

Reduces human effort and data collection requirements.

Abstract

Supervised deep networks are among the best methods for finding correspondences in stereo image pairs. Like all supervised approaches, these networks require ground truth data during training. However, collecting large quantities of accurate dense correspondence data is very challenging. We propose that it is unnecessary to have such a high reliance on ground truth depths or even corresponding stereo pairs. Inspired by recent progress in monocular depth estimation, we generate plausible disparity maps from single images. In turn, we use those flawed disparity maps in a carefully designed pipeline to generate stereo training pairs. Training in this manner makes it possible to convert any collection of single RGB images into stereo training data. This results in a significant reduction in human effort, with no need to collect real depths or to hand-design synthetic data. We can consequently train a stereo matching network from scratch on datasets like COCO, which were previously hard to exploit for stereo. Through extensive experiments we show that our approach outperforms stereo networks trained with standard synthetic datasets, when evaluated on KITTI, ETH3D, and Middlebury.