Yao Yao
Hello, I have updated all links. Would you try again? @duxingren14
@Tord-Zhang Yes that might be a problem. For training, such noises might not affect the training, but in testing, I think it would be better to filter them out using...
I have updated all links. Would you try whether it works now?
Hi @snavely, Thanks for your suggestion! We use a simple renderer to render the high-res images, and generate the low-res ones via image downsampling. I think both steps might cause...
> > @YoYo000首先，感谢您的精彩分享。 > > 我想为我的应用程序制作我自己的数据集，比如 dtu，但是我遇到了一些问题。 1、如何实现Depths文件夹下的Binary Image， 即dtu_training/Depths/scan1_train/depth_visual_0001.png。 > > 2、是否可以通过程序只使用raw image来创建Rectified文件夹中的7种不同光照的raw image，或者修改源程序preprocess.py是否可以只使用raw image。 > > 如果您能在繁忙的日程中抽出时间回复，我将不胜感激。 > > 请问能留下您的邮箱吗？有一些问题想要咨询您，真的不胜感激。 没太理解你的问题，我的邮箱是[email protected]，你可以写详细一点发给我
Thanks for holding the wechat group! I joined the group and may discuss with you in wechat.
@vgg4resnet have you joined the group? Or you could send you your wechat account then let me invite you
Hi @tatsy, The major difference between this repo and the two papers is the depth map fusion step. In the paper I described the fusion strategy as `visibility fusion -...
Exactly! The visibility fusion is described in Merrel's depth fusion paper. I would suggest first to try the visibility fusion - the variational refinement is actually a little complicated. BTW...
Hi Kevin, Have you solved the problem? It is noteworthy that the training cameras are different from the testing cameras. The training cameras are cropped/scaled in advance. So you may...