Vision Transformers for Dense Prediction
Paper • 2103.13413 • Published • 1
DPT 3.0 release
DPT 3.0 (MiDaS) models, leveraging ViT and ViT-hybrid backbones
-
Intel/dpt-large
Depth Estimation • 0.3B • Updated • 61.2k • 204Note This model leverages a Vision Transformer (ViT) backbone for monocular depth estimation.
Intel/dpt-hybrid-midas
Depth Estimation • Updated • 465k • 106Note This model leverages a hybrid Vision Transformer (ViT-hybrid) backbone for monocular depth estimation.