Prune Truong

Warp Consistency for Unsupervised Learning of Dense Correspondences

Prune Truong             Martin Danelljan            Fisher Yu             Luc Van Gool


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 will be released here.

How to cite:

  author    = {Prune Truong and
               Martin Danelljan and
               Fisher Yu and 
               Luc Van Gool},
  title     = {Warp Consistency for Unsupervised Learning of Dense Correspondences},
  year      = {2021},
  url       = {}
© Prune Truong 2021