TY - GEN
T1 - Unsupervised Non-Rigid Image Distortion Removal via Grid Deformation
AU - Li, Nianyi
AU - Thapa, Simron
AU - Whyte, Cameron
AU - Reed, Albert
AU - Jayasuriya, Suren
AU - Ye, Jinwei
N1 - Funding Information:
Acknowledgements. Li, Thapa and Ye are supported by NSF CRII-1948524, Louisiana Board of Regents grant LEQSF(2018-21)-RD-A-10, and a gift from DGene. Whyte and Jayasuriya are supported by NSF IIS-1909192. Reed was supported by a DoD NDSEG Fellowship.
Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Many computer vision problems face difficulties when imaging through turbulent refractive media (e.g., air and water) due to the refraction and scattering of light. These effects cause geometric distortion that requires either handcrafted physical priors or supervised learning methods to remove. In this paper, we present a novel unsupervised network to recover the latent distortion-free image. The key idea is to model non-rigid distortions as deformable grids. Our network consists of a grid deformer that estimates the distortion field and an image generator that outputs the distortion-free image. By leveraging the positional encoding operator, we can simplify the network structure while maintaining fine spatial details in the recovered images. Our method doesn't need to be trained on labeled data and has good transferability across various turbulent image datasets with different types of distortions. Extensive experiments on both simulated and real-captured turbulent images demonstrate that our method can remove both air and water distortions without much customization.
AB - Many computer vision problems face difficulties when imaging through turbulent refractive media (e.g., air and water) due to the refraction and scattering of light. These effects cause geometric distortion that requires either handcrafted physical priors or supervised learning methods to remove. In this paper, we present a novel unsupervised network to recover the latent distortion-free image. The key idea is to model non-rigid distortions as deformable grids. Our network consists of a grid deformer that estimates the distortion field and an image generator that outputs the distortion-free image. By leveraging the positional encoding operator, we can simplify the network structure while maintaining fine spatial details in the recovered images. Our method doesn't need to be trained on labeled data and has good transferability across various turbulent image datasets with different types of distortions. Extensive experiments on both simulated and real-captured turbulent images demonstrate that our method can remove both air and water distortions without much customization.
UR - http://www.scopus.com/inward/record.url?scp=85119949721&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119949721&partnerID=8YFLogxK
U2 - 10.1109/ICCV48922.2021.00252
DO - 10.1109/ICCV48922.2021.00252
M3 - Conference contribution
AN - SCOPUS:85119949721
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 2502
EP - 2512
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
Y2 - 11 October 2021 through 17 October 2021
ER -