Closed yd-yin closed 2 years ago
Indeed, all reconstructions are generated using an automated algorithm (as described in the paper). We include the point_cloud_quality_score in SequenceAnnotations. Make sure to use point clouds with this score being high.
Note that we plan to release a new version very soon with better foreground masks/point clouds, stay tuned.
Hello, please checkout the newly released version 2 of CO3D, it contains significantly improved segmentation masks.
Hi, thanks for your response and your great effort on this.
Hi, thanks for your great work on the big real-world dataset.
However, if you look at sequence
car/216_22790_47232
and other sequences, you will see that many of the foreground masks are wrongly annotated for background cars. Here, only 0038 and 0039 images are correct.So the corresponding point cloud
car/216_22790_47232/pointcloud.ply
is incorrect, either.This happens in most of the sequences in
car
. Maybe the annotating algorithm masks several cars and you only retain one?Will other categories be better?