cainsmile

> 我认为需要依据confidence的生成方式而定，回归方法（CVP）将每个像素点预测深度周围的四个深度假设层的权重之和作为confidence，而分类方法（R-MVSNet）或者我们的统一表示方法是将取所有假设层中的最大概率作为confidence。所以我们认为回归方法自然需要设置更大的prob_threshold来确保准确度。 那么最佳的参数是多少呢？可以复现得到你论文中的结果的值

I have fixed this problem. However, **the number of points I got is only half of the point clouds you provided**. Do you where the problem is?

> I tried to infer and fuse on DTU dataset, but found the predicted results are different from your released ply models. > > For example: Your released point cloud...

The results I showed are based on the **normal** filter. I have tried **gipuma** also, and I found the point clouds are much smaller than those you provided, so the...

Yeah, I just run the **test_dtu.sh** based on the pre-trained model you provided without any changes. I think there is something wrong with the installation of gipuma.

My environment is : python 3.8 pytorch 1.9.1 CUDA 10.1 opencv 3.3.1