Reproduce “Learning Parallax Attention for Stereo Image Super-Resolution” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Longguang Wang, Yingqian Wang, Zhengfa Liang, Zaiping Lin, Jungang Yang, Wei An, Yulan Guo
PASSRnet reconstructs high-resolution left-view images from low-resolution stereo pairs. It matches features across the full corresponding horizontal row, using parallax attention to transfer useful information from the right view without a preset disparity range. On KITTI 2015, at 2×, it reports 29.78 dB PSNR and 0.919 SSIM, versus StereoSR’s 29.09 dB and 0.909. The comparison covers 20 border-cropped test images.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.