leggedrobotics/defm
Image Feature Extraction • Updated • 527 • 10
DeFM
DeFM: depth foundation models for robotics. ViT and CNN encoders pretrained on 60M depth images, plus classification and segmentation benchmarks.
-
-
DeFM Feature PCA
🧊1Visualize DeFM depth foundation model features with PCA
-
DeFM: Learning Foundation Representations from Depth for Robotics
Paper • 2601.18923 • Published • 4 -
leggedrobotics/defm-bench-tartanground
Viewer • Updated • 1.2k • 19 -
leggedrobotics/defm-bench-graspnet
Viewer • Updated • 2.6k • 27 -
leggedrobotics/defm-bench-imagenet-depth
Preview • Updated • 17