TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/DeblurGAN: Blind Motion Deblurring Using Conditional Adver...

DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

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

2017-11-19CVPR 2018 6Deblurringobject-detectionObject Detection
PaperPDFCodeCodeCodeCodeCodeCodeCodeCode(official)CodeCodeCodeCodeCode

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 -- DeepDeblur. 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

Results

TaskDatasetMetricValueModel
DeblurringREDSAverage PSNR24.09DeblurGAN
DeblurringRealBlur-R (trained on GoPro)SSIM (sRGB)0.903DeblurGAN
DeblurringRealBlur-J (trained on GoPro)SSIM (sRGB)0.834DeblurGAN
2D ClassificationREDSAverage PSNR24.09DeblurGAN
2D ClassificationRealBlur-R (trained on GoPro)SSIM (sRGB)0.903DeblurGAN
2D ClassificationRealBlur-J (trained on GoPro)SSIM (sRGB)0.834DeblurGAN
10-shot image generationREDSAverage PSNR24.09DeblurGAN
10-shot image generationRealBlur-R (trained on GoPro)SSIM (sRGB)0.903DeblurGAN
10-shot image generationRealBlur-J (trained on GoPro)SSIM (sRGB)0.834DeblurGAN
Blind Image DeblurringREDSAverage PSNR24.09DeblurGAN
Blind Image DeblurringRealBlur-R (trained on GoPro)SSIM (sRGB)0.903DeblurGAN
Blind Image DeblurringRealBlur-J (trained on GoPro)SSIM (sRGB)0.834DeblurGAN

Related Papers

A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains2025-07-17RS-TinyNet: Stage-wise Feature Fusion Network for Detecting Tiny Objects in Remote Sensing Images2025-07-17Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection2025-07-17Dual LiDAR-Based Traffic Movement Count Estimation at a Signalized Intersection: Deployment, Data Collection, and Preliminary Analysis2025-07-17Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios2025-07-16Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping2025-07-15Generative Latent Kernel Modeling for Blind Motion Deblurring2025-07-12ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge2025-07-08