Sapiens Pose 0.6b Torchscript

🚀 Pose-Sapiens-0.6B-Torchscript

Sapiens is a vision transformer family pretrained on a large - scale human image dataset, which can be fine - tuned for human - centric vision tasks and shows excellent generalization ability.

🚀 Quick Start

The Pose-Sapiens-0.6B-Torchscript model is designed for keypoint detection, specifically estimating 308 keypoints (body + face + hands + feet) on a single image.

✨ Features

• Sapiens is a family of vision transformers pretrained on 300 million human images at 1024 x 1024 image resolution. When fine - tuned for human - centric vision tasks, it generalizes well to in - the - wild conditions.
• Sapiens - 0.6B natively supports 1K high - resolution inference. The models can perform well on in - the - wild data, even with scarce or entirely synthetic labeled data.

📚 Documentation

Model Details

• Developed by: Meta
• Model type: Vision Transformer
• License: Creative Commons Attribution - NonCommercial 4.0
• Task: pose
• Format: torchscript
• File: sapiens_0.6b_goliath_best_goliath_AP_609_torchscript.pt2

Model Card

More Resources

• Repository: https://github.com/facebookresearch/sapiens
• Paper: https://arxiv.org/abs/2408.12569
• Demo: https://huggingface.co/spaces/facebook/sapiens-pose
• Project Page: https://about.meta.com/realitylabs/codecavatars/sapiens
• Additional Results: https://rawalkhirodkar.github.io/sapiens
• HuggingFace Collection: https://huggingface.co/collections/facebook/sapiens-66d22047daa6402d565cb2fc

📄 License

This model is released under the Creative Commons Attribution - NonCommercial 4.0 license.