Retrieval Robust to Object Motion Blur

• URL: http://arxiv.org/abs/2404.18025v2
• Date: Wed, 17 Jul 2024 21:57:16 GMT
• Title: Retrieval Robust to Object Motion Blur
• Authors: Rong Zou, Marc Pollefeys, Denys Rozumnyi,
• Abstract summary: We propose a method for object retrieval in images that are affected by motion blur. We present the first large-scale datasets for blurred object retrieval. Our method outperforms state-of-the-art retrieval methods on the new blur-retrieval datasets.
• Score: 54.34823913494456
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Towards Reflected Object Detection: A Benchmark [5.981658448641905]
  This paper introduces a benchmark specifically designed for Reflected Object Detection. Our Reflected Object Detection dataset (RODD) features a diverse collection of images showcasing reflected objects in various contexts. RODD encompasses 10 categories and includes 21,059 images of real and reflected objects across different backgrounds.
  arXiv  Detail & Related papers  (2024-07-08T03:16:05Z)
• The Background Also Matters: Background-Aware Motion-Guided Objects Discovery [2.6442319761949875]
  We propose a Background-aware Motion-guided Objects Discovery method. We leverage masks of moving objects extracted from optical flow and design a learning mechanism to extend them to the true foreground. This enables a joint learning of the objects discovery task and the object/non-object separation.
  arXiv  Detail & Related papers  (2023-11-05T12:35:47Z)
• Discovering Objects that Can Move [55.743225595012966]
  We study the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions. We choose to focus on dynamic objects -- entities that can move independently in the world.
  arXiv  Detail & Related papers  (2022-03-18T21:13:56Z)
• Contrastive Object Detection Using Knowledge Graph Embeddings [72.17159795485915]
  We compare the error statistics of the class embeddings learned from a one-hot approach with semantically structured embeddings from natural language processing or knowledge graphs. We propose a knowledge-embedded design for keypoint-based and transformer-based object detection architectures.
  arXiv  Detail & Related papers  (2021-12-21T17:10:21Z)
• UAV Images Dataset for Moving Object Detection from Moving Cameras [0.0]
  This paper presents a new high resolution aerial images dataset in which moving objects are labelled manually. It aims to contribute to the evaluation of the moving object detection methods for moving cameras.
  arXiv  Detail & Related papers  (2021-03-21T18:44:38Z)
• A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection [56.82077636126353]
  We take advantage of object-centric images to improve object detection in scene-centric images. We present a simple yet surprisingly effective framework to do so. Our approach can improve the object detection (and instance segmentation) accuracy of rare objects by 50% (and 33%) relatively.
  arXiv  Detail & Related papers  (2021-02-17T17:27:21Z)
• FMODetect: Robust Detection and Trajectory Estimation of Fast Moving Objects [110.29738581961955]
  We propose the first learning-based approach for detection and trajectory estimation of fast moving objects. The proposed method first detects all fast moving objects as a truncated distance function to the trajectory. For the sharp appearance estimation, we propose an energy minimization based deblurring.
  arXiv  Detail & Related papers  (2020-12-15T11:05:34Z)
• DeFMO: Deblurring and Shape Recovery of Fast Moving Objects [139.67524021201103]
  generative model embeds an image of the blurred object into a latent space representation, disentangles the background, and renders the sharp appearance. DeFMO outperforms the state of the art and generates high-quality temporal super-resolution frames.
  arXiv  Detail & Related papers  (2020-12-01T16:02:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.