# Specialized for human images
Sapiens Depth 0.3b Torchscript
Sapiens is a family of vision transformers pre-trained on 300 million 1024 x 1024 resolution human images for depth estimation tasks.
3D Vision English
S
facebook
69
0
Sapiens Depth 1b Torchscript
Sapiens is a vision transformer series model pre-trained on 300 million 1024 x 1024 resolution human images, focusing on human-centric vision tasks.
3D Vision English
S
facebook
160
0
Featured Recommended AI Models