zhu2bowen

How to create demo LR images？

1

请问作者，主页的样例上的退化图是由由Jpeg退化函数从高清图获取的吗？我想获得类似的退化图像具体应该怎么操作？

Are the ret landmarks suitable to compute EAR？ more see https://pyimagesearch.com/2017/04/24/eye-blink-detection-opencv-python-dlib/ def eye_aspect_ratio(eye): # compute the euclidean distances between the two sets of # vertical eye landmarks (x, y)-coordinates A...

20:54 kwephis2148189 noise_flow_model E=30 tr=494.6 ts=67.6 tsm=471.8 tv=0.0 T=1034.2 tL=-14214.2 sL=-14450.6 smL=-10295.5 SDr=1.0 SDs=0.9 B=1 0.679,0.785,0.969,0.000 It is my first time get a minus loss, and I donnot know why...

Thanks for your greate work, my question is as the title. Clean image, Noise image , Noise as follows(Sorry, I cannnot upload it, )

About the model of API "https://photoroom.com/api"

4

Thanks for your excellent work firstly! I use rembg as a library, and model_name is "u2net.onnx"。I found the out image is very different from the result of API "https://photoroom.com/api". So,...

still found bad pixeles in movie subtitles area after retrain

1

First of all, thank you for your outstanding work! I would like to use the model to infer images from moives and TV shows. After adding captions to the dataset,...

#see the image 

首先感谢提供这么优秀的项目。看论文中说有计划把压缩损失加入退化学习范围，请问现在是否可实现？或者计划合适实现呢？