Xuan Zhang

Hi, Lambert Glad that you tried it out. Unfortunately I have really no experience with depth cameras other than asus xtion. So I am not able to fix your issue....

You may try to stream color image to topic "/camera/rgb/image_raw" and depth image to topic "camera/depth_registered/image_raw". If you want to don't want to use SLAM (i.e. launch only semantic_cloud.py &...

Hi, I did't encountered this issue during the work so I don't know how to solve this exactly. Apparently there is a library not found in your system. I think...

Hi, Yes, it is possible. In fact it was what we intended to do. The problem is that the depth estimated by monocular SLAM is relative (i.e. not in meters...

Stereo camera could work as ORB-SLAM2 supports stereo cameras. Semantic segmentation is done based on RGB image. Depth information is only required for SLAM and reconstruction. We used Asus xtion...

It should be an Asus Xtion Live. I have no idea if it was a PRO version and the camera is no longer with me. Sorry for that. Anyway, I...

You didn't install ```octomap``` library properly. Try ```sh rosdep install semantic_slam ```

Please refer to issue #2 .

Thank you for the reply. I may not understand the code completely. Is supervision data sampled from the entire time domain or just from the first few time steps? The...

Hi, Thanks for your interest. The paper you referred corresponds to our kddcup solution: https://github.com/divelab/MoleculeX/tree/molx/BasicProp/kddcup2021 The code for conformer generation is here: https://github.com/divelab/MoleculeX/blob/29951d711f2923feb60914147feb450e2c0c922f/BasicProp/kddcup2021/conformer/gen_confs.py#L30