Seeing-Motion-in-the-Dark
Seeing-Motion-in-the-Dark copied to clipboard
cchen156
Seeing Motion in the Dark. ICCV19
test-video results blues images and test-image results images have strange green color
Thank you for providing this data set. i want use the raw data,but i don't know the data range , black level and raw pattern.Can you give a brief description...
In the test stage, the test dynamic frames are pre-processed using the exposure ratio determined by its corresponding long-exposure frame. The result seems fine. But for arbitrary scene, since we...
in train.py and pretrain_on_small.py, the following codes: ` vgg_fake1=build_vgg19(255*out_small[0:1,:,:,::-1], reuse=True) vgg_fake2=build_vgg19(255*out_small[1:2,:,:,::-1], reuse=True)` take the network's outputs as the RGB image input. Should not `out_small` be clipped or normalized to 0~255...
Can you provide file parts in Baidu Drive like "Learning to see in the dark"? Since I always failed to download the dataset even the 11G "long" part.
Hi, thank you very much for the code you provided. When I reproduced this paper pytorch, I found that each predicted picture will have 1 to 3 small apertures. Do...
when my dataset is an raw image which bayer pattern is 'BGGR',I want to know how to convert my dataset to the input of this model (why the input shape...
In the last paragraph of section 4, you say "Noise is reduced using spatial and temporal correlations in preprocessing by VBM4D." So I want to confirm that the preprocessing include...
In your paper, you mentioned that you training data has been captured by using a Sony RX100 VI camera. > We used a Sony RX100 VI camera, which can capture...
