Basile Van Hoorick

Yes, the published dataset does not contain all modalities because the total size would be ~17 TB otherwise, instead of 2.4 TB. I am generating the archive with the additional...

Please see the update here: https://gcd.cs.columbia.edu/#datasets I clarified the description as follows: The basic modalities are: RGB, depth, semantic segmentation, instance segmentation, and 2D bounding boxes. The additional modalities are:...

As far as I know from playing around with it myself, when you load an optical flow PNG frame as RGBA, the channels have the following meaning: ``` # frame...

Hi, If you have a custom video and wish to run the model with specified camera rotation and translation parameters, I would recommend running `infer.py` as documented here: https://github.com/basilevh/gcd?tab=readme-ov-file#custom-data-no-gt You...