ReversibleHalftoning
ReversibleHalftoning copied to clipboard
The first approach to utilize CNN for image dithering, which is actually non-trivial. This formulation enables us to equip it with extra features, e.g. reversibility. [ICCV 2021]
您好,我想训练这个ReversibleHalftoning代码查看一下这个半色调结果,在warm-up阶段时需要用到的逆半色调网络预训练的数据,但是预训练的相关数据包下载下来是损坏的,请问您能重新发一个没有损坏的包吗?
Hi! It's a nice work and achieves amazing results! I would like to try the model by myself. But when I try to download the model_best.pth.tar, the zip file seems...
您好,我对您的这个工作非常感兴趣,想了解下 训练数据halftone的goundthruth是怎么生成的呢?
When comparing halftone images in terms of PSNR and SSIM (for example, Ostromoukhov method, Structure-aware halftoning, and this paper method), you have mentioned that "Higher PSNR/SSIM indicate better quality". I...
Hi, thanks for your great work. I'm interesting about the spetral property of your generated reversible halftones. Could you please tell me how to caculate the radially averaged power spectral...
请教
你好!打扰一下,我想请问一下,你的模型中是否可以做到用神经网络将RGB图像转换成半色调图像呢?也就是论文中提到的前半部分。
错误提示:randn_like() received an invalid combination of arguments - got (bool), but expected one of: * (Tensor input, torch.dtype dtype, torch.layout layout, torch.device device, bool requires_grad) 这是为什么呀 生成随机高斯噪声时,x[1]是一个bool值,但程序需要的是一个张量
您好,我在使用训练好的模型权重时发现模型文件损坏,model_best.pth.tar的大小只有 25 字节,通过不同方式下载不同网络,还是损坏的应该不是网络的问题,您方便再发一份吗?