yxt132
yxt132
It's been quite a while since the author created this repo. Do you have expected date for code release?
It's been quite a while since the author created this repo. Do you have expected date for code release?
Hi, what trimaps did you use for testing? did you use the trimaps provided by Adobe or the trimaps generated from alpha, similar to the training process?
This is nice work. However, we observed some artifacts along the edges in the image. Below is one example, anyone has seen the same thing and has any idea about...
We ran into an error in the middle of the training process. We used 1 1080ti gpu with batch size of 16 (image size 256x256). But the training got killed...
Any progress on the training? When do you expect to release the pre-trained model? can't wait to see the results! thanks!
Datasets
Hi, great work! Do you have scheduled timeline for releasing the datasets?
Great idea. However, i tried it on mobilnet-v2 with several images. It does not work well. How can we guarantee the upsampling from feature map to the original image size,...
Great work in re-implementing the white-box model using pytorch. However, after testing, I found the results are not good as the official version by the authors. There is still a...
Nice work! Would you consider releasing the real world dataset you collected for text removal? Thanks!