CVLGAug 10, 2019

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

arXiv:1908.03826v11111 citationsHas Code
AI Analysis

This addresses the problem of slow deblurring for applications like video processing, though it is incremental as it builds on prior GAN-based methods.

They tackled single image motion deblurring by developing DeblurGAN-v2, which achieves 10-100 times faster processing than competitors while maintaining close to state-of-the-art quality, enabling real-time video deblurring.

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

Code Implementations6 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes