DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better

Abstract

We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility. DeblurGAN-v2 is based on a relativistic conditional GAN with a double-scale discriminator. For the first time, we introduce the Feature Pyramid Network into deblurring, as a core building block in the generator of DeblurGAN-v2. It can flexibly work with a wide range of backbones, to navigate the balance between performance and efficiency. The plug-in of sophisticated backbones (e.g., Inception-ResNet-v2) can lead to solid state-of-the-art deblurring. Meanwhile, with light-weight backbones (e.g., MobileNet and its variants), DeblurGAN-v2 reaches 10-100 times faster than the nearest competitors, while maintaining close to state-of-the-art results, implying the option of real-time video deblurring. We demonstrate that DeblurGAN-v2 obtains very competitive performance on several popular benchmarks, in terms of deblurring quality (both objective and subjective), as well as efficiency. Besides, we show the architecture to be effective for general image restoration tasks too. Our codes, models and data are available at: https://github.com/KupynOrest/DeblurGANv2

Accepted in ICCV 2019

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• YOLOv3: An Incremental Improvement
• The relativistic discriminator: a key element missing from standard GAN
• EnlightenGAN: Deep Light Enhancement without Paired Supervision
• Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal
• Deep $k$-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
• Gated Fusion Network for Joint Image Deblurring and Super-Resolution
• Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
• From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur

Cited by in corpus (6)

• Multi-Stage Progressive Image Restoration
• MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis
• Unpaired Image Super-Resolution using Pseudo-Supervision
• SiamEvent: Event-based Object Tracking via Edge-aware Similarity Learning with Siamese Networks
• Prior-enlightened and Motion-robust Video Deblurring
• Implicit Subspace Prior Learning for Dual-Blind Face Restoration