Retrieval Robust to Object Motion Blur
This addresses a practical problem for computer vision applications dealing with real-world images containing moving objects, but it is incremental as it adapts retrieval techniques to a specific, previously unaddressed scenario.
The paper tackles the problem of retrieving motion-blurred objects in images, which is unexplored in computer vision, by proposing a method that learns robust representations to match blurred and deblurred objects, and it outperforms state-of-the-art methods on new large-scale blur-retrieval datasets.
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.