CookMaker

Hello Chen, thanks for your excellent work! I'm writing to ask some question about the combination of the line vector and the plane mat in density pipeline. Why this process...

The loss is really small,but the result is weird

8

Thanks for this excellent work! I am using instant-ngp to accelerate the training speed. And i think the loss is really small enough to get a nice image. here is...

I am learning the scene part in this excellent work. But I found that the empty_space_loss in paper is like that:  But in our code,it's like: ``` coarse_empty_space_loss =...

So many pretrained models

4

What does the 'X' in latest_net_G_X mean?? There are so many pretrained models.Which should i choose?Or they are all required?

A question about the ngp pose, and related problem.

8

您好！您的工作非常精彩，通过阅读源代码使我收益颇多 这里想请教一下： 1）输入NeRF中的pose以及推理中使用的原视频的pose指的到底是什么呢？是头部的三维姿态吗？我只能确定它不是landmark 2）在我的实验中发现：由于推理中的眨眼与原始pose的眨眼频率并不同，这导致了原视频在眨眼时，人脸会出现异常的抖动现象，这个抖动现象是否有办法消除呢？我使用debug模式查看后发现抖动现象出现时landmark并没有异常，那么是pose造成的吗？ 非常期待您的回复，希望您可以指点一二

Hello,I found you implemented the GAN loss part, I also want to try it in my training. Could you please share the download link of the ckpt？

Hi, thanks for your excellent work. I found that the d-nerf dataset's mesh face number is different across time frames. Does this not correspond to the alignment in the paper?...

## 注意 Pull Request 提交后，预计 1 分钟内将会得到自动化格式检查的结果。只有通过自动化检查的 Pull Request 才会被人工审核。 - [是 ] 请确保此 Pull Request 能够通过自动化代码检查。 ## 签署 必须签署下面的对话框才能开始审核。 ### HowToCook 仓库采用了 [The Unlicense](https://unlicense.org/) 协议 菜谱在签入前，必须确保其可以**直接声明进入 "公共领域"（public domain)**。这意味着一旦合并后，任何人都**可以**自由复制，修改，发布，使用，编译，出售或以菜谱的形式或菜的形式分发，**无论**是出于**商业目的**还是**非商目的**，以及**任何**手段。 -...