Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring

TL;DR

This paper introduces the MISC Filter, a novel motion-adaptive deblurring model that estimates spatially-variant motion flow to effectively remove complex real-world motion blur, outperforming existing methods.

Contribution

The paper proposes a new motion-adaptive separable collaborative filtering approach that jointly estimates motion flow and performs spatially differentiated deblurring, addressing limitations of prior residual-based models.

Findings

Achieves state-of-the-art results on four benchmark datasets.

Effectively handles complex, spatially variable motion blur.

Demonstrates robustness across diverse real-world scenarios.

Abstract

Eliminating image blur produced by various kinds of motion has been a challenging problem. Dominant approaches rely heavily on model capacity to remove blurring by reconstructing residual from blurry observation in feature space. These practices not only prevent the capture of spatially variable motion in the real world but also ignore the tailored handling of various motions in image space. In this paper, we propose a novel real-world deblurring filtering model called the Motion-adaptive Separable Collaborative (MISC) Filter. In particular, we use a motion estimation network to capture motion information from neighborhoods, thereby adaptively estimating spatially-variant motion flow, mask, kernels, weights, and offsets to obtain the MISC Filter. The MISC Filter first aligns the motion-induced blurring patterns to the motion middle along the predicted flow direction, and then collaboratively filters the aligned image through the predicted kernels, weights, and offsets to generate the output. This design can handle more generalized and complex motion in a spatially differentiated manner. Furthermore, we analyze the relationships between the motion estimation network and the residual reconstruction network. Extensive experiments on four widely used benchmarks demonstrate that our method provides an effective solution for real-world motion blur removal and achieves state-of-the-art performance. Code is available at https://github.com/ChengxuLiu/MISCFilter