NTIRE 2024 Challenge on Stereo Image Super-Resolution: Methods and Results
This challenge addresses the problem of enhancing stereo image quality for applications like 3D vision, but it is incremental as it builds on existing SR challenges.
The paper tackled stereo image super-resolution (SR) with a x4 magnification under computational constraints, establishing a new benchmark where 14 and 13 teams achieved PSNR scores better than the baseline in two tracks.
This paper summarizes the 3rd NTIRE challenge on stereo image super-resolution (SR) with a focus on new solutions and results. The task of this challenge is to super-resolve a low-resolution stereo image pair to a high-resolution one with a magnification factor of x4 under a limited computational budget. Compared with single image SR, the major challenge of this challenge lies in how to exploit additional information in another viewpoint and how to maintain stereo consistency in the results. This challenge has 2 tracks, including one track on bicubic degradation and one track on real degradations. In total, 108 and 70 participants were successfully registered for each track, respectively. In the test phase, 14 and 13 teams successfully submitted valid results with PSNR (RGB) scores better than the baseline. This challenge establishes a new benchmark for stereo image SR.