Introducing DeFM: a foundation model for depth images, built for robotics
ETH Robotic Systems Lab introduces DeFM, a foundation model for depth images designed for robotics applications. The model includes weights, code, and a browser demo, offering a new tool for depth-based perception and learning in robotic systems.
DeFM represents a new approach to vision foundation models tailored for robotics, focusing on depth images rather than RGB data. This shift could improve perception and learning in environments where depth information is critical, such as navigation and manipulation tasks.
Source: ETH Robotic Systems Lab — X · Read original article ↗
Article text · Original source · English
Introducing DeFM: a foundation model for depth images, built for robotics.
Weights, code and a browser demo are out!
Vision foundation models like DINO and SigLip now power much of robot learning. But they are built for RGB. What about depth? Introducing DeFM: a foundation model for depth images, built for robotics. 🌐 https://de-fm.github.io Weights, code, and demo are out today 🧵View the quoted post on X
Source：Robotic Systems Lab · x.com