Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

将fastmode设置为false后图像的插帧效果不佳 #307

Open
Liming-belief opened this issue Apr 11, 2023 · 3 comments
Open

将fastmode设置为false后图像的插帧效果不佳 #307

Liming-belief opened this issue Apr 11, 2023 · 3 comments

Comments

@Liming-belief
Copy link

我对两张图像进行插帧,在fastmode设置为false后,生成的结果不佳,请问是什么原因导致的。
img1
同时在output中保存的原始图像img0与img1质量有些退化,是什么原因导致的。

@hzwer
Copy link
Owner

hzwer commented Apr 11, 2023

if not fastmode:
     print('contextnet is removed')
    '''
    c0 = self.contextnet(img0, flow[:, :2])
    c1 = self.contextnet(img1, flow[:, 2:4])
    tmp = self.unet(img0, img1, warped_img0, warped_img1, mask, flow, c0, c1)
    res = tmp[:, :3] * 2 - 1
    merged[3] = torch.clamp(merged[3] + res, 0, 1)
    '''

在当前版本 v4.6 中,fastmode=false 理论上只会打印出一行提示信息
以视觉效果为目标的所有模型都推荐使用 fastmode,原因是 refinenet 基本上只是提升 psnr 指标而降低视觉效果

@Liming-belief
Copy link
Author

你好,对于两帧图像相差较大的情况下,插帧的结果边缘较为模糊,请问有什么改进方法吗

@hzwer
Copy link
Owner

hzwer commented Apr 11, 2023

你可以考虑用 FILM 方法,他们针对这样的情况进行了优化
https://github.com/google-research/frame-interpolation

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants