Sapiens Depth 0.3b Bfloat16

🚀 Depth-Sapiens-0.3B-Bfloat16

Sapiens is a vision transformer family pretrained on 300 million high - resolution human images. This model can estimate relative depth on human images.

🚀 Quick Start

The Depth-Sapiens-0.3B-Bfloat16 model is designed for depth estimation on human images. It's based on the Sapiens family of vision transformers, which are pretrained on a large - scale human image dataset.

✨ Features

• Sapiens is pretrained on 300 million human images at 1024 x 1024 resolution, enabling it to generalize well to in - the - wild conditions when fine - tuned for human - centric vision tasks.
• The Sapiens - 0.3B model natively supports 1K high - resolution inference and shows excellent generalization even with scarce or synthetic labeled data.

📚 Documentation

Model Details

• Developed by: Meta
• Model type: Vision Transformer
• License: Creative Commons Attribution - NonCommercial 4.0
• Task: depth
• Format: bfloat16
• File: sapiens_0.3b_render_people_epoch_100_bfloat16.pt2

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. Sapiens - 0.3B natively support 1K high - resolution inference. The resulting models exhibit remarkable generalization to in - the - wild data, even when labeled data is scarce or entirely synthetic.

Model Card

More Resources

• Repository: https://github.com/facebookresearch/sapiens
• Paper: https://arxiv.org/abs/2408.12569
• Demo: [https://huggingface.co/spaces/facebook/sapiens - depth](https://huggingface.co/spaces/facebook/sapiens - depth)
• 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](https://huggingface.co/collections/facebook/sapiens - 66d22047daa6402d565cb2fc)

💻 Usage Examples

Basic Usage

The Depth 0.3B model can be used to estimate relative depth on human images. The specific code implementation may depend on the actual application scenario and the framework used.

📄 License

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