NeRT: Implicit Neural Representations for General Unsupervised Turbulence Mitigation
This addresses the challenge of generalizing turbulence mitigation across static scenes, dynamic scenes, and text reconstructions for computer vision and optics applications, though it appears incremental as it builds on existing implicit neural representation techniques.
The paper tackles the problem of atmospheric and water turbulence mitigation in images by proposing NeRT, an implicit neural representation method that reconstructs clean images from dozens of distorted inputs without supervision. It outperforms state-of-the-art methods on various datasets and achieves a 48× speedup for video sequences.
The atmospheric and water turbulence mitigation problems have emerged as challenging inverse problems in computer vision and optics communities over the years. However, current methods either rely heavily on the quality of the training dataset or fail to generalize over various scenarios, such as static scenes, dynamic scenes, and text reconstructions. We propose a general implicit neural representation for unsupervised atmospheric and water turbulence mitigation (NeRT). NeRT leverages the implicit neural representations and the physically correct tilt-then-blur turbulence model to reconstruct the clean, undistorted image, given only dozens of distorted input images. Moreover, we show that NeRT outperforms the state-of-the-art through various qualitative and quantitative evaluations of atmospheric and water turbulence datasets. Furthermore, we demonstrate the ability of NeRT to eliminate uncontrolled turbulence from real-world environments. Lastly, we incorporate NeRT into continuously captured video sequences and demonstrate $48 \times$ speedup.