Adaptive Quantile Sparse Image (AQuaSI) Prior for Inverse Imaging Problems
This addresses the challenge of representing natural image distributions more effectively for computer vision and image processing tasks, though it appears incremental as an improvement over existing priors.
The authors tackled the problem of finding better priors for ill-posed inverse imaging problems by proposing the Adaptive Quantile Sparse Image (AQuaSI) prior, which demonstrated efficacy in applications like joint RGB/depth upsampling and RGB/NIR image restoration.
Inverse problems play a central role for many classical computer vision and image processing tasks. Many inverse problems are ill-posed, and hence require a prior to regularize the solution space. However, many of the existing priors, like total variation, are based on ad-hoc assumptions that have difficulties to represent the actual distribution of natural images. Thus, a key challenge in research on image processing is to find better suited priors to represent natural images. In this work, we propose the Adaptive Quantile Sparse Image (AQuaSI) prior. It is based on a quantile filter, can be used as a joint filter on guidance data, and be readily plugged into a wide range of numerical optimization algorithms. We demonstrate the efficacy of the proposed prior in joint RGB/depth upsampling, on RGB/NIR image restoration, and in a comparison with related regularization by denoising approaches.