Work

DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

Year: 2018

Type: conference-paper

Abstract: We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss. DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance. The quality of the deblurring model is also evaluated in a novel way on a real-world problem - object detection on (de-)blurred images. The method is 5 times faster than the closest competitor - Deep-Deblur [25]. We also introduce a novel method for generating synthetic motion blurred images from sharp ones, allowing realistic dataset augmentation. The model, code and the dataset are available at https://github.com/KupynOrest/DeblurGAN.

Source: IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI: 10.1109/cvpr.2018.00854

Authors: Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiri Matas

Institution: Ukrainian Catholic University

Language: English

Topic: Advanced Image Processing Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Grantová Agentura České Republiky, Bundesministerium für Wissenschaft, Forschung und Wirtschaft, Bundesministerium für Verkehr, Innovation und Technologie

Awards: G1751925659, Center for Large Scale Multi-modal Data Interpretation