1st Place Solutions for UG2+ Challenge 2022 ATMOSPHERIC TURBULENCE MITIGATION
This work addresses atmospheric turbulence mitigation for computer vision applications, but it is incremental as it adapts existing methods like Restormer and NIMA to this specific challenge.
The paper tackled the problem of reconstructing high-quality images from frames distorted by atmospheric turbulence, achieving an average accuracy of 98.53% on text pattern reconstruction and ranking first in the UG2+ Challenge.
In this technical report, we briefly introduce the solution of our team ''summer'' for Atomospheric Turbulence Mitigation in UG$^2$+ Challenge in CVPR 2022. In this task, we propose a unified end-to-end framework to reconstruct a high quality image from distorted frames, which is mainly consists of a Restormer-based image reconstruction module and a NIMA-based image quality assessment module. Our framework is efficient and generic, which is adapted to both hot-air image and text pattern. Moreover, we elaborately synthesize more than 10 thousands of images to simulate atmospheric turbulence. And these images improve the robustness of the model. Finally, we achieve the average accuracy of 98.53\% on the reconstruction result of the text patterns, ranking 1st on the final leaderboard.