LIU Qingming

How to efficiently debug while developing my own models.

11

Hi, Thanks to your wonderful work on this framework! I want to develop my own model according to my idea. Previously, I usually use IDE like Pycharm（ where I could...

Consideration of function "w2pers" in Neural Points module?

5

Hi, Charlie, thanks for your awesome work of PointNeRF. But I had a question about the code In "w2pers" function of NeuralPoints.py. According to my understanding and your codes，"point_xyz" is...

Question About “nearest_view” function when init Pcd from colmap

2

 Hi，Charlie！ 谢谢你的工作，当我在使用Colmap创建的点云（或者是像scannet一样从depth中初始化点云）的时候，在train_ft.py中会调用一个nearest_view 函数，我理解的这个函数的目的是计算每个点属于哪一个view。便于后面使用query_embeding函数去提取初始特征。那么我的问题：在倒数第三行这里对“点云方向和相机中心像素点方向的内积“ 与 “点到campos的距离” 进行了一个加权处理。请问为什么这里距离的权重是1/200，您在这里是怎么考虑的呢，适合应用到什么样的数据集上面？我可不可以任意调整这个数。

Some questions about dataset details

1

1. 请问您的tranform_full.json文件是怎么转换得到的，Colmap直接导出的结果的格式似乎不是这样的，。 2. 请问为什么您只对C2w矩阵进行了变换（将YZ轴方向翻转，从OpenCV坐标系变换到opencl坐标系），但是使用PointCloud初始化voxel的时候对PointCloud却没有进行坐标轴的变换呢？(是不是您已经对PointCloud文件进行了这样的处理再保存的？)

Hi！ Thanks for your wonderful work. In your paper, it says:"Note that, the recent Semantic-NeRF (Zhi et al., 2021a) is also not comparable because it only learns 3D semantic categories,...

Update neus.py

2

#this make sure it will be saved after training, if not, when execute test scripts by setting '--test', this hyperparameter will be set to zero, Which will cause significant drops...

Different Results When testing On NeuS.

2

Hi, benny! I meet a strange error. I tried to train NeuS on several scenes. After training, your codes will automatical excute the evalueation like the codes below. ` if...

thank you for your nice work! I would like to query that when will you release your code?

About the translation of camera in HyperNeRF dataset and coords convention

2

Hi, Thanks for your wonderful work. 1. in your codes line 164-165 of `scene/hyper_loader.py` , you use` T = - camera.position @ R` instead of `T = camera.position `,Could your...

Thank you for your nice work. your rasterizer seems cannot render depth. do you plan to update ?