co3d icon indicating copy to clipboard operation
co3d copied to clipboard

Filter accurate pointclouds

Open theamaya opened this issue 1 year ago • 6 comments

Hello,

Your paper mentions that a set of accurate pointclouds for each category has been selected. Where can I find the labels for these accurate pointclouds that passed your filtering?

theamaya avatar May 25 '23 07:05 theamaya

Hi, each point cloud has a point cloud quality score. You can find these scores in the sequence_annotation.jgz files. To get the best pointclouds, I would suggest taking the ones with the highest scores.

davnov134 avatar May 25 '23 10:05 davnov134

Thank you for your reply. However, even after downloading the entire dataset, the sequence_annotation.jgz files for each category appear to contain details for very few sequences per category.

Eg:

for 'backpack' category - {"sequence_name": "537_78249_152122", "category": "backpack", "video": null, "point_cloud": null, "viewpoint_quality_score": NaN}

would you please tell me what am I missing?

theamaya avatar May 26 '23 07:05 theamaya

This sounds weird, are you sure that you downloaded the entire co3d? If yes, can you run the following example and check that the loaded sequence annotations contain many entries for backpacks? https://github.com/facebookresearch/co3d/blob/main/examples/print_co3d_stats.py

You can also run the following example to show backpack sequences: https://github.com/facebookresearch/co3d/blob/main/examples/show_co3d_dataset.py

davnov134 avatar Jun 06 '23 10:06 davnov134

Hi, how about the camera pose scores ? Is the higher the better ? Also, how well do the scores of point cloud correlate with camera pose scores ?

jh27kim avatar Nov 02 '23 04:11 jh27kim

The scores are indeed the higher the better. They were both regressed based on COLMAP outputs, so probably do correlate.

shapovalov avatar Nov 02 '23 11:11 shapovalov

Right, thank you for clarification.

jh27kim avatar Nov 03 '23 06:11 jh27kim