High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling, ECCV 2020

Yu Zeng$^1$, Zhe Lin$^2$, Jimei Yang$^2$, Jianming Zhang$^2$, Eli Shechtman$^2$, Huchuan Lu$^1$

1 Dalian University of Technology,

2 Adobe Research

Results Web App REST API Paper Supplementary Material Comparison

High-resolution results (≥1024)

Synthetic samples | Removing real objects

Synthetic samples

8wlymn.jpg 8wl0Sg.jpg 8wlqk6.jpg 8wlBlQ.jpg 8wlTmR.jpg 8wlDyj.jpg 8wlrOs.jpg 8wldfS.jpg 8wlcT0.jpg 8wl2kV.jpg 8wlRYT.jpg 8wlhpF.jpg 8wl4l4.jpg 8wlLtK.jpg 8wlHTx.jpg 8wlOfO.jpg 8wljpD.jpg

Removing real objects

8wQG5T.jpg 8wQIdP.jpg 8wQhqI.jpg 8wQWMd.jpg 8wlELR.jpg



Effect of specifying the include or avoid region:


mode_img = img.mode
mode_msk = mask.mode

W, H = img.size
str_img = img.tobytes().decode("latin1")
str_msk = mask.tobytes().decode("latin1")

data = {'str_img': str_img, 'str_msk': str_msk, 'width':W, 'height':H, 
        'mode_img':mode_img, 'mode_msk':mode_msk}
# Enable upsample
#data = {'str_img': str_img, 'str_msk': str_msk, 'str_include':None, 'str_avoid':str_avoid, 'width':W, 'height':H, #'mode_img':mode_img, 'mode_msk':mode_msk, 'is_refine': True}

r = requests.post('', json=data)

download python example

Supplementary Material