Introducing Theia: a vision foundation model for robotics developed by our team at the Institute. Theia enables robots to learn and adapt more quickly and effectively by refining knowledge from multiple off-the-shelf vision models into compact representations for classification, segmentation, depth prediction, and other modalities—all at a lower computation cost. Learn more at https://lnkd.in/enccz9GE.
Ueli Schläpfer
1mo
Hey - already have a kitchen like that, the kids would certainly love to teach the robot! ;-) On the more serious side, this looks really interesting. Excited to see where this goes and to when we have a use case in one of our manipulation projects.
Rajendra Patel
1mo
Excellent work
Akmal Abbas
1mo
Impressive
Engineer. Technologist.
1moCombining the application of another model, such as Nvidia's FoundationPose, with Theia's capabilities, can potentially expand the range of possible use cases. I can't help but wonder about that.