Chao YIN (尹 超)

icon indicating a website link https://scholar.google.com/citations?user=MD3X7kwAAAAJ icon indicating an email [email protected]

icon location Assistant Professor at the Guangzhou Institute of Geography. Interests: 1) Point cloud processing, 2) Deep learning, 3) BIM modeling, 4) GIS & AEC software

Results 8 comments of Chao YIN (尹 超)

about visualization

> > Two questions about the visualiztion part. > > > > 1. `pc_utils.py` can not run properly. Base on the code, the reason is `load_data` function is not defined...

Where is the code?

Hi? I have re-implemented the SQN work and achieved comparable performance on S3DIS to the paper. You can check my [SQN_tensorflow](https://github.com/PointCloudYC/SQN_tensorflow) repo.

looking forward to pytorch version

Hi? In case someone might need to find a tensorflow re-implementation, please check my [SQN_tensorflow](https://github.com/PointCloudYC/SQN_tensorflow) repo. As for the Pytorch version, I have re-implemented the SQN using CloserLook3D repo as...

Annotation cost for 1‰ label. For a dataset with dense points

>For example, one of the rooms in S3DIS has over 9,000,000 points. Does that mean that you're going to annotate 9000 points for that scene? Yes, it is true. But...

Visualization

Thanks for your attention to our work! You can use the utils/visualize_data.py code for visualization.

How to run the program

Sorry to reply late. Have you done the contents of the requirements section including setting up a conda environment and install the custom CUDA operators ? After this, prepare the...

the model inference

No, but with a simple trick, you can do the inference. Just prepare the inference data as the validation data was prepared and assume the datat all belong to one...

Is the AziNorm method applicable to the indoor or outdoor datasets (S3DIS or Semantic3D)?

Sorry for the late reply. Thanks for your insightful comments. So you have concern that the indoor dataset (S3DIS) might not possess the radial symmetry property as one area point...