The instance_dataset_gen from ywangeq

instance_dataset_gen's Introduction

Hi there 👋

🔭 我目前在思谋科技工作,我们是一家致力于将计算机视觉落地于工业场景的AI科技公司:wink:
🌱 如果你对计算机视觉落地工业有浓厚的兴趣，欢迎给我们投递简历，丰富的校招&社招岗位，base 北京 上海 深圳 香港 海外任你选：详细岗位.
📫 内推email我

Stats

instance_dataset_gen's People

Contributors

Stargazers

instance_dataset_gen's Issues

hello i think your code has so many mistakes

can you upload useful new version? thanks so much

Can this method work on S3DIS?

Hi
Can it work on Dataset S3DIS?

Don't see the file mentioned in ReadME

Hello, you said this project is your code to generate spherical images from raw lidar point clouds. But i can't find the code file . Am i missing something? Hope for your answer . Many thanks.

Performance against original spherical data.

Hi,

I was just trying your latest revision of the code & I have a couple questions.

In comparison to the original released spherical data, I noticed the generated numpy file somewhat outputs only one output file for one sync folder, whereas the original would have one numpy file for each .bin file. May I know the intuition behind this?
Also, how do you compare the file generated from your code against the said spherical data. I was simply thinking of running either Squeeze/PointSeg against both sets of data & comparing the performance, but I wondered if you have other methods.

Some details about the code

instance_dataset_gen/Test_data/gene_data.py

Line 69 in 5fc2edb

x_min = -w/2.

Hello, in this line i noticed that in the coordinate system of velodyne, x may related to l and y may related to w, as what you did in get_boxcorners function. Am i wrong ? Hope for your reply, many thanks.

Recommend Projects