LODE: Deep Local Deblurring and A New Benchmark

TL;DR

This paper introduces a new dataset and a novel deep learning framework for local image deblurring, focusing on moving objects, and demonstrates significant improvements over existing methods.

Contribution

The paper presents the first local deblurring dataset and a flexible, attention-guided network that enhances local deblurring performance.

Findings

BladeNet improves PSNR by 2.5dB on local deblurring tasks.

The LODE dataset contains 3,700 real-world local blur images.

Framework is compatible with existing state-of-the-art algorithms.

Abstract

While recent deep deblurring algorithms have achieved remarkable progress, most existing methods focus on the global deblurring problem, where the image blur mostly arises from severe camera shake. We argue that the local blur, which is mostly derived from moving objects with a relatively static background, is prevalent but remains under-explored. In this paper, we first lay the data foundation for local deblurring by constructing, for the first time, a LOcal-DEblur (LODE) dataset consisting of 3,700 real-world captured locally blurred images and their corresponding ground-truth. Then, we propose a novel framework, termed BLur-Aware DEblurring network (BladeNet), which contains three components: the Local Blur Synthesis module generates locally blurred training pairs, the Local Blur Perception module automatically captures the locally blurred region and the Blur-guided Spatial Attention module guides the deblurring network with spatial attention. This framework is flexible such that it can be combined with many existing SotA algorithms. We carry out extensive experiments on REDS and LODE datasets showing that BladeNet improves PSNR by 2.5dB over SotAs for local deblurring while keeping comparable performance for global deblurring. We will publish the dataset and codes.