Soft Warping Based Unsupervised Domain Adaptation for Stereo Matching

Haoyuan Zhang, Lap Pui Chau, Danwei Wang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

7 Citations (Scopus)


Stereo matching is a practical method to estimate depth information and retrieve 3D world in robot perception and autonomous driving scenarios. With the development of convolution neural networks (CNNs), deep-learning based stereo matching algorithms have significantly improved the accuracy and dominated most of the online benchmarks. However, limited labels in real world, especially in challenging weather conditions, still hinder the technology from practical usage. In this paper, we propose a new unsupervised learning mechanism for stereo matching, utilizing adversarial iterative learning and novel soft warping loss to promote the effectiveness of the networks in unseen environments. The experiments transferring the stereo matching module from synthetic domain to real-world domain demonstrate the superiority of our proposed method. Extensive experiments in challenging weathers further prove that our method shows great practical potential in strait environments.

Original languageEnglish
Article number9527141
Pages (from-to)3835-3846
Number of pages12
JournalIEEE Transactions on Multimedia
Publication statusPublished - Aug 2022
Externally publishedYes


  • adversarial learning
  • soft warping loss
  • stereo matching
  • unsupervised domain adaptation

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Soft Warping Based Unsupervised Domain Adaptation for Stereo Matching'. Together they form a unique fingerprint.

Cite this