Simultaneous Deep Stereo Matching and Dehazing with Feature Attention

Taeyong Song, Youngjung Kim, Changjae Oh, Hyunsung Jang, Namkoo Ha, Kwanghoon Sohn

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)


Unveiling the dense correspondence under the haze layer remains a challenging task, since the scattering effects result in less distinctive image features. Contrarily, dehazing is often confused by the airlight-albedo ambiguity which cannot be resolved independently at each pixel. In this paper, we introduce a deep convolutional neural network that simultaneously estimates a disparity and clear image from a hazy stereo image pair. Both tasks are synergistically formulated by fusing depth information from the matching cost and haze transmission. To learn the optimal fusion of depth-related features, we present a novel encoder-decoder architecture that extends the core idea of attention mechanism to the simultaneous stereo matching and dehazing. As a result, our method estimates high-quality disparity for the stereo images in scattering media, and produces appearance images with enhanced visibility. Finally, we further propose an effective strategy for adaptation to camera-captured images by distilling the cross-domain knowledge. Experiments on both synthetic and real-world scenarios including comparisons with state-of-the-art methods demonstrate the effectiveness and flexibility of our approach.

Original languageEnglish
Pages (from-to)799-817
Number of pages19
JournalInternational Journal of Computer Vision
Issue number4
Publication statusPublished - 2020 Apr 1

Bibliographical note

Publisher Copyright:
© 2020, Springer Science+Business Media, LLC, part of Springer Nature.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'Simultaneous Deep Stereo Matching and Dehazing with Feature Attention'. Together they form a unique fingerprint.

Cite this