Announcing the Matterport3D Dataset of Labeled 3D Spaces for Machine Learning
1–4 of 4 posts
Re: Announcing the Matterport3D Dataset of Labeled 3D Spaces for Machine Learning
#2This is rad! Got any ideas of stuff that can be done with this using Keras?
Re: Announcing the Matterport3D Dataset of Labeled 3D Spaces for Machine Learning
#3This is rad! Got any ideas of stuff that can be done with this using Keras?
Lots of things! Since 3D convolutional networks are very limited in their maximum resolution, most of the interesting things you can do involve learning on RGB+D images via a 2D CNN. A lot of tasks on images (segmentation, identification etc) are easier when you have even partial depth data as input.
Re: Announcing the Matterport3D Dataset of Labeled 3D Spaces for Machine Learning
#4This is rad! Got any ideas of stuff that can be done with this using Keras?
Lots of things! Since 3D convolutional networks are very limited in their maximum resolution, most of the interesting things you can do involve learning on RGB+D images via a 2D CNN. A lot of tasks on images (segmentation, identification etc) are easier when you have even partial depth data as input.
If you didn't see the link to the paper, it's here: https://arxiv.org/pdf/1709.06158.pdf A wide range of usecases are discussed there.