Motion-Aware Adaptive Pixel Pruning for Efficient Local Motion Deblurring

TL;DR

This paper introduces a novel, efficient local motion deblurring method that adaptively identifies blurred regions and reduces computational costs through pixel pruning and structural reparameterization, achieving superior results.

Contribution

The paper presents a trainable mask predictor and intra-frame motion analyzer for adaptive, efficient local motion deblurring with end-to-end training and significant FLOPs reduction.

Findings

Outperforms state-of-the-art methods on local and global blur datasets.

Reduces FLOPs by 49% compared to leading models.

Achieves superior deblurring quality with efficient computation.

Abstract

Local motion blur in digital images originates from the relative motion between dynamic objects and static imaging systems during exposure. Existing deblurring methods face significant challenges in addressing this problem due to their inefficient allocation of computational resources and inadequate handling of spatially varying blur patterns. To overcome these limitations, we first propose a trainable mask predictor that identifies blurred regions in the image. During training, we employ blur masks to exclude sharp regions. For inference optimization, we implement structural reparameterization by converting $3\times 3$ convolutions to computationally efficient $1\times 1$ convolutions, enabling pixel-level pruning of sharp areas to reduce computation. Second, we develop an intra-frame motion analyzer that translates relative pixel displacements into motion trajectories, establishing adaptive guidance for region-specific blur restoration. Our method is trained end-to-end using a combination of reconstruction loss, reblur loss, and mask loss guided by annotated blur masks. Extensive experiments demonstrate superior performance over state-of-the-art methods on both local and global blur datasets while reducing FLOPs by 49\% compared to SOTA models (e.g., LMD-ViT). The source code is available at https://github.com/shangwei5/M2AENet.