Retrieval Robust to Object Motion Blur

TL;DR

This paper introduces a novel object retrieval method that effectively matches motion-blurred objects with their sharp counterparts, supported by new large-scale datasets and extensive experiments demonstrating superior performance over existing methods.

Contribution

The paper presents the first large-scale datasets for blurred object retrieval and a robust representation learning approach that handles motion blur in images.

Findings

Outperforms state-of-the-art retrieval methods on blur datasets

Effective matching of blurred objects to sharp images

Validated on large-scale, diverse datasets

Abstract

Moving objects are frequently seen in daily life and usually appear blurred in images due to their motion. While general object retrieval is a widely explored area in computer vision, it primarily focuses on sharp and static objects, and retrieval of motion-blurred objects in large image collections remains unexplored. We propose a method for object retrieval in images that are affected by motion blur. The proposed method learns a robust representation capable of matching blurred objects to their deblurred versions and vice versa. To evaluate our approach, we present the first large-scale datasets for blurred object retrieval, featuring images with objects exhibiting varying degrees of blur in various poses and scales. We conducted extensive experiments, showing that our method outperforms state-of-the-art retrieval methods on the new blur-retrieval datasets, which validates the effectiveness of the proposed approach. Code, data, and model are available at https://github.com/Rong-Zou/Retrieval-Robust-to-Object-Motion-Blur.