Open sunohm opened 1 year ago
Thanks for your interest. We use stacked convolutional blocks to build the encoder.
感谢你的回复,我看了补充材料里面体系结构详细信息,图四U-Net architecture 是整体结构吗
light&£ @.***
------------------ 原始邮件 ------------------ 发件人: "fenglinglwb/SDM" @.>; 发送时间: 2023年2月28日(星期二) 上午9:34 @.>; @.**@.>; 主题: Re: [fenglinglwb/SDM] 网络结构 (Issue #3)
Thanks for your interest. We use stacked convolutional blocks to build the encoder.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
Exactly.
好的,谢谢,我还是有点迷糊,通过整体结构看,解码器是使用的StyleGAN中的D吗?
light&£ @.***
------------------ 原始邮件 ------------------ 发件人: "fenglinglwb/SDM" @.>; 发送时间: 2023年2月28日(星期二) 上午9:50 @.>; @.**@.>; 主题: Re: [fenglinglwb/SDM] 网络结构 (Issue #3)
Exactly.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
Yep. We use StyleGAN 2 as the decoder.
对于文章,编码器卷积堆叠而成是噪声扩散过程,解码器是去除噪声的过程是这样吗?那是使用StyleGAN2的生成器作为encoder-decoder架构的解码器吗?
light&£ @.***
------------------ 原始邮件 ------------------ 发件人: "fenglinglwb/SDM" @.>; 发送时间: 2023年2月28日(星期二) 上午10:17 @.>; @.**@.>; 主题: Re: [fenglinglwb/SDM] 网络结构 (Issue #3)
Yep. We use StyleGAN 2 as the decoder.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
Our model is NOT a denoising diffusion model. Diffusion-based methods in traditional inpainting work refer to gradually propagating useful information from undamaged regions to missing regions. We follow this line and name our model a spatial diffusion network.
好的,非常感谢。
light&£ @.***
------------------ 原始邮件 ------------------ 发件人: "fenglinglwb/SDM" @.>; 发送时间: 2023年2月28日(星期二) 中午11:34 @.>; @.**@.>; 主题: Re: [fenglinglwb/SDM] 网络结构 (Issue #3)
Our model is NOT a denoising diffusion model. Diffusion-based methods in traditional inpainting work refer to gradually propagating useful information from undamaged regions to missing regions. We follow this line and name our model a spatial diffusion network.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
你好,这篇论文模型没不太明白,想请教一下,网络整体结构是采用编码器解码器结构,解码器使用的styleGAN,那编码器是是卷积块堆叠起来的,还是使用的unet,希望得到你的回复。