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. 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
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Orest Kupyn (add twitter)
Tetiana Martyniuk (add twitter)
Junru Wu (add twitter)
Zhangyang Wang (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

1. (comment) 12/05/19 12:59AM

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
08/12/19 06:06PM
6,085
2,499
Tweets
jp_axs4ll: RT @mtmthh: Come to our poster #124! DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better Arxiv: https://t.co/qWUM4Qgwzr Code…
artsiom_s: RT @mtmthh: Come to our poster #124! DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better Arxiv: https://t.co/qWUM4Qgwzr Code…
mtmthh: Come to our poster #124! DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better Arxiv: https://t.co/qWUM4Qgwzr Code: https://t.co/Fba9DbcDvF #iccv2019 #iccv19 https://t.co/CGHE36KJXx
subhobrata1: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
arxiv_pop: 2019/08/10 投稿 3位 CV(Computer Vision and Pattern Recognition) DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better https://t.co/5Xepl8q3Rl 9 Tweets 15 Retweets 59 Favorites
Pol09122455: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
arxiv_cs_LG: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better. Orest Kupyn, Tetiana Martyniuk, Junru Wu, and Zhangyang Wang https://t.co/5hL4UcmOw1
sdemyanov: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
iamknighton: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
jackieshi1: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
thomasjelonek: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
KageKirin: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
jmsl: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
arxivml: "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better", Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhang… https://t.co/nzaHL0yAgk
hey_kishore: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
Memoirs: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better. https://t.co/q0jvyiCRZN
caymanlee: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
_bautie_tek_: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
fanks_vision: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
arxiv_cs_LG: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better. Orest Kupyn, Tetiana Martyniuk, Junru Wu, and Zhangyang Wang https://t.co/5hL4UcmOw1
UkiwhY: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
nrose: RT @roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17U…
roadrunning01: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better pdf: https://t.co/09FBCBSpI6 abs: https://t.co/VkqIV17UP2 github: https://t.co/Uhc2TzjLIs https://t.co/Uk7RqjZNkl
BrundageBot: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better. Orest Kupyn, Tetiana Martyniuk, Junru Wu, and Zhangyang Wang https://t.co/eCmkQTDJjH
Images
Related