NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results
It establishes a new benchmark for stereo image super-resolution, addressing the problem for researchers and practitioners in computer vision.
The paper summarizes the NTIRE 2022 Challenge on Stereo Image Super-Resolution, where 21 teams competed to restore details in low-resolution stereo images, with 20 teams achieving PSNR scores better than the baseline.
In this paper, we summarize the 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results. This challenge has 1 track aiming at the stereo image super-resolution problem under a standard bicubic degradation. In total, 238 participants were successfully registered, and 21 teams competed in the final testing phase. Among those participants, 20 teams successfully submitted results with PSNR (RGB) scores better than the baseline. This challenge establishes a new benchmark for stereo image SR.