Zhihao Liang
Zhihao Liang
@nicolas-chaulet Would you like to share how you plan to implement the super-voxel clustering algorithm? Using pcl or others library, I am actually most interested in this for this work....
> I was more thinking of using scikit learn for that or some basic clustering toolbox. Adding PCL as a dependency is not a good idea in general and it...
> Can't we just use segmentation tool from ScanNet repository for this? Do you mean the [segmentator](https://github.com/ScanNet/ScanNet/tree/master/Segmentator)? It sounds good. And can it be used for other datasets?I see its...
> > > Can't we just use segmentation tool from ScanNet repository for this? > > > > > > Do you mean the [segmentator](https://github.com/ScanNet/ScanNet/tree/master/Segmentator)? It sounds good. And can...
And the coco_dataset? It seems need to convert coco into voc's type
> @lzhnb Would you also like to reproduce the result in COCO dataset or COCO to VOC setting? Maybe we can tackle it together. Here is my email [[email protected]](mailto:[email protected]) I...
Well, I use the `Image` to `imread` the `c++`'s output and `save` as a new image, this new image is equal to the `python`'s result. Doest this mean the `Image`...
Hi, thank you very much for your attention to our work. I also foresee that someone will ask S3DIS related questions, so I hope to give a unified reply to...
You are right. The 0-dim of `superpoint` ids should be equal to `xyz`'s. And superpoint generation in **superpoint_graph** will vocalize the point cloud S3DIS first, so it will downsample the...
> Hi, Could you please share your code on S3DIS datasets? I would be grateful if you could do that for me I am in dire need of the code...