Stereoscopic Image Super-Resolution with Stereo Consistent Feature


  • Wonil Song Yonsei University
  • Sungil Choi Yonsei University
  • Somi Jeong Yonsei University
  • Kwanghoon Sohn Yonsei University



We present a first attempt for stereoscopic image super-resolution (SR) for recovering high-resolution details while preserving stereo-consistency between stereoscopic image pair. The most challenging issue in the stereoscopic SR is that the texture details should be consistent for corresponding pixels in stereoscopic SR image pair. However, existing stereo SR methods cannot maintain the stereo-consistency, thus causing 3D fatigue to the viewers. To address this issue, in this paper, we propose a self and parallax attention mechanism (SPAM) to aggregate the information from its own image and the counterpart stereo image simultaneously, thus reconstructing high-quality stereoscopic SR image pairs. Moreover, we design an efficient network architecture and effective loss functions to enforce stereo-consistency constraint. Finally, experimental results demonstrate the superiority of our method over state-of-the-art SR methods in terms of both quantitative metrics and qualitative visual quality while maintaining stereo-consistency between stereoscopic image pair.




How to Cite

Song, W., Choi, S., Jeong, S., & Sohn, K. (2020). Stereoscopic Image Super-Resolution with Stereo Consistent Feature. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12031-12038.



AAAI Technical Track: Vision