Our newest "from Photos" model is here - delivering unmatched precision in 3D body shape and pose accuracy from any photo. To make the most of this update, check out our new credit bundles, supercharge your PRO subscription and create even more avatars.
<aside>
🏆 What our customers are saying about our “Avatars from Photos” product:
We just achieved 100% fit on a new suit design using your avatars for 4D Fit!
- Apparel customer developing smart-garment technologies
</aside>
attachment:dcd3c85a-3826-428b-954b-a97c04ae88ed:AFI-2_V1.mp4
Map of this Document 🗺️
Express Mode is an exciting new feature designed to adapt to any clothing, any environment. This method is capable of extracting the 3D human body mesh with SOTA accuracy. It works with a vast variety of clothing styles, including loose or non-form fitting garments.
Powered by BEDLAM, an innovative neural network-based method for creating 3D avatars and synthetic data that we use to train our own neural-network to generate accurate 3D body meshes and body measurements. This mode allows you to wear your preferred outfit and not be confined to a specific environment.
Source image
Express mode result
Our Avatars from Photos method (AFP) delivers measurable and impactful improvements in pose and shape accuracy compared to leading methods in academia, making it a robust solution for diverse real-world and expressive applications.
You can find the most recent benchmark results of our current model used in “Express Mode” on the following page:
Avatars from Photos - Benchmark
Following you will find which image(s) work best for the classic and express mode, as well as general best practices in order to achieve high accuracy.