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

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... (read more)

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Deblurring GoPro DeblurGANv2-Inception PSNR 29.55 # 16
SSIM 0.934 # 12
Deblurring GoPro DeblurGANv2-MobileNet-DSC PSNR 28.03 # 21
SSIM 0.922 # 16
Deblurring GoPro DeblurGANv2-MobileNet PSNR 28.17 # 20
SSIM 0.925 # 15
Deblurring HIDE (trained on GOPRO) DeblurGAN-v2 PSNR (sRGB) 26.61 # 8
SSIM (sRGB) 0.875 # 7
Deblurring RealBlur-J DeblurGAN-v2 SSIM (sRGB) 0.870 # 3
PSNR (sRGB) 29.69 # 3
Deblurring RealBlur-J (trained on GoPro) DeblurGAN-v2 PSNR (sRGB) 28.70 # 1
SSIM (sRGB) 0.866 # 3
Deblurring RealBlur-R DeblurGAN-v2 PSNR (sRGB) 36.44 # 3
SSIM (sRGB) 0.935 # 3
Deblurring RealBlur-R (trained on GoPro) DeblurGAN-v2 PSNR (sRGB) 35.26 # 5
SSIM (sRGB) 0.944 # 4

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions
GAN
Generative Models