Mex.Wayne

I seems to meet the same problem and what I did is to rebuild the video I split the video into images by python script and rebuild the video by...

> Do you find it easier to follow something like [QEMU's rewrite of float divide](https://qemu-project.gitlab.io/qemu/src/S/2646.html#L1728) or [the sqrt function](https://qemu-project.gitlab.io/qemu/src/S/2646.html#L3454)? We worked quite hard to ensure the eventual generated code is...

> > > Do you find it easier to follow something like [QEMU's rewrite of float divide](https://qemu-project.gitlab.io/qemu/src/S/2646.html#L1728) or [the sqrt function](https://qemu-project.gitlab.io/qemu/src/S/2646.html#L3454)? We worked quite hard to ensure the eventual generated...

> when run ‘python main_ViDeNN.py --use_gpu=1 --checkpoint_dir=ckpt_videnn --save_dir='./test_data/result/frame1_videnn' --test_dir='./test_data/test/frame1'’，the image after denoising is abnormal. original image  denoised iamge  excuse me, what is the reason? 还好看到你的结果，不然我也就花时间复现效果了

>  I‘ve got even worse results than you，I will give up this work （T_T）

> when run ‘python main_ViDeNN.py --use_gpu=1 --checkpoint_dir=ckpt_videnn --save_dir='./test_data/result/frame1_videnn' --test_dir='./test_data/test/frame1'’，the image after denoising is abnormal. original image  denoised iamge  excuse me, what is the reason? I've got the normal...

 looking at the black area in train window， the results not as good as the paper shows

oh，I have read your paper again. Well, the motion area which have no t-1 frame for reference will perform worse than static area. the windows of the train is just...

me three