PReNet icon indicating copy to clipboard operation
PReNet copied to clipboard

Progressive Image Deraining Networks: A Better and Simpler Baseline (CVPR 2019)

Results 24 PReNet issues
Sort by recently updated
recently updated
newest added

请问,文章中提到的损失函数递归监督是怎么实现的呀?没有思路

定义的PReNet 和 PReNet_LSTM 两个网络结构没有区别?

测试数据集的rainy_image是在哪里?网盘里没有

Hi. Does Rain100L training dataset only has 200 images? Rain100L in other paper seems to have 1800 images for training. Does this problem affect the experimental results?

作者你好 请问最后处理视频的那个视频在哪里下载呢 谢谢

可以给下论文上的两张真实的数据集图片吗?

作者你好,在network.py中上述四个网络结构,为什么输出的时候倒数第三行的结果要加上input呢?x = x + input,这个应该是已经derain后的结果,在加上输入的图,是不是多余了?

您好我用rain100H训练100个epoch后并且测试出来的指标只有PSNR=28.0568,似乎并没有达到论文中29.46这么高

Hi, thank you for your contribution! Will the training set of Rain12600 be trained 100 epochs. Then tested on data set 1400? Looking forward to your reply, thanks.

您好作者,请问文件夹 ./PReNet/logs/real/中的两组参数PReNet1.pth和PReNet2.pth是在哪个数据集上训练出来的?