xiaoxingzeng / DF2Net

DF2Net: A Dense-Fine-Finer Network for Detailed 3D Face Reconstruction
122 stars 17 forks source link

code #2

Closed lxzkeyan closed 4 years ago

lxzkeyan commented 4 years ago

Thank you for sharing the code.But I especially looking forward to the release of the code.

xiaoxingzeng commented 4 years ago

Thank you for sharing the code.But I especially looking forward to the release of the code.

Thanks for your interest, the code and model are uploaded now.

lxzkeyan commented 4 years ago

Thanks for sharing the code.But can you share the training code?Finally, I am looking forward to your reply.Thanks. Email address: lxz_nxu@163.com.

------------------ 原始邮件 ------------------ 发件人: "xiaoxingzeng"<notifications@github.com>; 发送时间: 2019年11月18日(星期一) 晚上11:28 收件人: "xiaoxingzeng/DF2Net"<DF2Net@noreply.github.com>; 抄送: "云不知深处"<846281856@qq.com>;"Author"<author@noreply.github.com>; 主题: Re: [xiaoxingzeng/DF2Net] code (#2)

Thank you for sharing the code.But I especially looking forward to the release of the code.

The code and model is released now.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

lxzkeyan commented 4 years ago

The pretraining model and the shape_predictor_68_face_landmarks which  website cannot be opened.

------------------ 原始邮件 ------------------ 发件人: "xiaoxingzeng"<notifications@github.com>; 发送时间: 2019年11月18日(星期一) 晚上11:28 收件人: "xiaoxingzeng/DF2Net"<DF2Net@noreply.github.com>; 抄送: "云不知深处"<846281856@qq.com>;"Author"<author@noreply.github.com>; 主题: Re: [xiaoxingzeng/DF2Net] code (#2)

Thank you for sharing the code.But I especially looking forward to the release of the code.

The code and model is released now.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

xiaoxingzeng commented 4 years ago

@lxzkeyan Hi, I add links of baidu drive in the README

lxzkeyan commented 4 years ago

Thank you for your reply.Can you share the training code?I'm especially looking forward to your sharing the training code.

------------------ 原始邮件 ------------------ 发件人: "xiaoxingzeng"<notifications@github.com>; 发送时间: 2019年11月20日(星期三) 上午10:55 收件人: "xiaoxingzeng/DF2Net"<DF2Net@noreply.github.com>; 抄送: "云不知深处"<846281856@qq.com>;"Mention"<mention@noreply.github.com>; 主题: Re: [xiaoxingzeng/DF2Net] code (#2)

@lxzkeyan Hi, I add links of baidu drive in the README

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

liwei46 commented 4 years ago

@xiaoxingzeng

How about the 70k image-depth pair dataset? Thanks.

xiaoxingzeng commented 4 years ago

@liwei46 , I found that, the size of our training data is about 100G, so maybe I can release the data generation code and upload some examples.

xiaoxingzeng commented 4 years ago

@lxzkeyan , It is easy to reimplement our training process, and I upload the most complicate sfs loss related code in https://github.com/xiaoxingzeng/DF2Net_SfS_Computing