Warp Consistency for Unsupervised Learning of Dense Correspondences

TL;DR

This paper introduces Warp Consistency, an unsupervised learning method for dense correspondence that effectively handles large appearance and viewpoint changes, achieving state-of-the-art results on multiple benchmarks.

Contribution

It proposes a novel warp consistency loss that enables unsupervised training of dense correspondence networks on real images with large variations.

Findings

Sets new state-of-the-art on MegaDepth, RobotCar, and TSS benchmarks.

Effective in geometric and semantic matching tasks.

Validates the approach by training three recent dense correspondence networks.

Abstract

The key challenge in learning dense correspondences lies in the lack of ground-truth matches for real image pairs. While photometric consistency losses provide unsupervised alternatives, they struggle with large appearance changes, which are ubiquitous in geometric and semantic matching tasks. Moreover, methods relying on synthetic training pairs often suffer from poor generalisation to real data. We propose Warp Consistency, an unsupervised learning objective for dense correspondence regression. Our objective is effective even in settings with large appearance and view-point changes. Given a pair of real images, we first construct an image triplet by applying a randomly sampled warp to one of the original images. We derive and analyze all flow-consistency constraints arising between the triplet. From our observations and empirical results, we design a general unsupervised objective employing two of the derived constraints. We validate our warp consistency loss by training three recent dense correspondence networks for the geometric and semantic matching tasks. Our approach sets a new state-of-the-art on several challenging benchmarks, including MegaDepth, RobotCar and TSS. Code and models are at github.com/PruneTruong/DenseMatching.