ghost-free-shadow-removal
ghost-free-shadow-removal copied to clipboard
vinthony
[AAAI 2020] Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
when I use pre-trained model to test data augmentation, but It's results will be so noise and color is incorrect. What step I loss? Thanks for your help!
In the paper, you have mentioned that each convolutional block for the DHAN follows by an Instance Normalization (IN) and LeakyReLU layer, however, it uses Batch Normalization here instead. https://github.com/vinthony/ghost-free-shadow-removal/blob/93cc1d68c1870def781f4aabc208a38d0869766e/networks.py#L25...
Would you please share the method to extract the mask from the image pair (shadow and shadow-free)?
It's a great job! As you mentioned for the SRD masks, "Hi, we also use a simple rule to extract the mask from the image pair." Would you please share...
Hi - I'm using my own dataset at 640x480 to train, and I run out of memory almost immediately on my GPU, an RTX 2070 Super - I get a...
Dear all, I tried to run the DEMO ipynb file to test the results. After loading 2 pairs of images (still with shades), I get the following error: "Cannot feed...
Hi, Here are some of my questions 1. How to use your model to remove the shadow of the image with the resolution of 1920*1080 ? 2. I have achieved...
Hi, It seems vgg-19-verydeep is resource hungry. So I wanted to replace it with another simple model. I tried vgg-16-verydeep and vgg-f in the same web page you mentioned in...
Hi Team, Thanks for the awesome solution. I went through your previous issues resolving OOM (resizing of images) & the TensorFlow version used. (< 2.x) Python version I used for...
Hi there, congrats on the great paper! I wonder if you can provide the results of the model trained on the AISTD dataset where the testing images are kept as...
