DocScanner
DocScanner copied to clipboard
The official repo for “DocScanner: Robust Document Image Rectification with Progressive Learning”.
请发送到邮箱[email protected] 感激不尽
Hello, Thank you for your great work. Could you please let me know when you will release the details code and training testing methods?
Thanks for the great job, I wonder how to train the model with my own dataset?How to bulid the dataset?And how to train the model?
hello,output features shape is b,128,H/8,W/8, downsampled warping flow shape is b,2,H/8,W/8 ,but Fk shape is b,128,H/8,W/8.What is the connection method? how to get the Fk?
just like the title, i'm a senior student who's really interested in the topic of paper-dewarping. i love your previous fantastic work. looking forward to the code of DocScanner
Hi, can you tell me where the dataset is placed and the steps to train the dataset? Thanks in advance for sharing!
它对于正常图片效果是不好的,能不能得到他们的倾斜角呢?