# 2nd Place Solutions for UG2+ Challenge 2022 -- D3Net for Mitigating Atmospheric Turbulence from Images

arXiv: https://arxiv.org/abs/2208.12332 · HTML: https://mlsanity.com/paper/2208.12332/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 8 references that are in the map.
- First posted on arXiv 25 Aug 2022.

## Builds on (most cited first, 5 of 5)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels](https://mlsanity.com/paper/1903.12529/) (2019)
- [Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform](https://mlsanity.com/paper/2107.11627/) (2021)
- [NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results](https://mlsanity.com/paper/2204.09314/) (2022)

## Abstract (arXiv)

This technical report briefly introduces to the D3Net proposed by our team "TUK-IKLAB" for Atmospheric Turbulence Mitigation in UG2+ Challenge at CVPR 2022. In the light of test and validation results on textual images to improve text recognition performance and hot-air balloon images for image enhancement, we can say that the proposed method achieves state-of-the-art performance. Furthermore, we also provide a visual comparison with publicly available denoising, deblurring, and frame averaging methods with respect to the proposed work. The proposed method ranked 2nd on the final leader-board of the aforementioned challenge in the testing phase, respectively.