license: cc-by-nc-4.0
language:
- en
Model Card for Sapiens
Sapiens is a family of vision transformers pretrained on 300 million human images at 1024 x 1024 image resolution.
The pretrained models when finetuned for human-centric vision tasks generalize to in-the-wild conditions.
Model Details
Model Description
Sapiens, a family of models for four fundamental human-centric vision tasks - 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-resolution inference and are extremely easy to adapt for individual tasks by simply fine-tuning models pretrained on over 300 million in-the-wild human images. The resulting models exhibit remarkable generalization to in-the-wild data, even when labeled data is scarce or entirely synthetic. Our simple model design also brings scalability - model performance across tasks improves as we scale the parameters from 0.3 to 2 billion. Sapiens consistently surpasses existing baselines across various human-centric benchmarks.
- Developed by: Meta
- Model type: Vision Transformers
- License: Creative Commons Attribution-NonCommercial 4.0
Model Sources
- Repository: https://github.com/facebookresearch/sapiens
- Paper: https://arxiv.org/abs/2408.12569
Uses
- pose estimation (keypoints 17, keypoints 133, keypoints 308)
- body-part segmentation (28 classes)
- depth estimation
- surface normal estimation