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.
Bibliographical noteFunding Information:
This research was supported by R&D program for Advanced Integrated-intelligence for Identification (AIID) through the National Research Foundation of KOREA (NRF) funded by Ministry of Science and ICT (NRF-2018M3E3A1057289).
© 2020, Springer Science+Business Media, LLC, part of Springer Nature.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Artificial Intelligence