CAR-Net: A Cascade Refinement Network for Rotational Motion Deblurring under Angle Information Uncertainty

TL;DR

CAR-Net introduces a cascade refinement neural network for rotational motion deblurring that effectively handles angle uncertainty through progressive residual correction and optional angle detection, demonstrating superior results on synthetic and real images.

Contribution

The paper presents a novel cascade refinement architecture for semi-blind rotational deblurring that incorporates an angle detection module and progressive residual correction.

Findings

Effective in reducing artifacts and restoring details

Works well with noisy angle information

Validated on synthetic and real-world images

Abstract

We propose a new neural network architecture called CAR-net (CAscade Refinement Network) to deblur images that are subject to rotational motion blur. Our architecture is specifically designed for the semi-blind scenarios where only noisy information of the rotational motion blur angle is available. The core of our approach is progressive refinement process that starts with an initial deblurred estimate obtained from frequency-domain inversion; A series of refinement stages take the current deblurred image to predict and apply residual correction to the current estimate, progressively suppressing artifacts and restoring fine details. To handle parameter uncertainty, our architecture accommodates an optional angle detection module which can be trained end-to-end with refinement modules. We provide a detailed description of our architecture and illustrate its efficiency through experiments using both synthetic and real-life images. Our code and model as well as the links to the datasets are available at https://github.com/tony123105/CAR-Net