Augmented Reality technology startup ModiFace unveiled their deep learning-based live video hair tracking and hair color simulation that is ideal for the beauty industry.
“We have been working on deep learning architectures for a long time now, and recent advances in both the neural network architectures, basic hardware level optimizations, as well as the availability of significant training data, have made photo-realistic video hair tracking and coloration possible,” said Parham Aarabi, CEO of ModiFace and Professor at the University of Toronto.
Using GTX 1080 TI GPUs and cuDNN, the team trained their collaborative neural networks on 220,000 carefully annotated hair images — the largest such database in the world. Their networks detect hair in each video frame and adjust the coloration of hair in a photorealistic way.
“We are extremely excited to offer live hair coloration and style alteration to our brand partners. The accuracy and realism of this new technology will forever change how hair color is tried on, explored, and purchased by consumers. We expect the first brands to leverage this technology to launch within the next few months,” said Aarabi whose company powers over 200 custom augmented reality apps for beauty brands such as Sephora, Estée Lauder, Allergan, L’Oreal, Unilever, and Coty.
The new technology is available for iPhone and iPad within ModiFace’s “Hair Color” app.
Read more >
Related resources
- GTC session: WonderJourney: Going from Anywhere to Everywhere
- GTC session: Production Rendering on GPU with Arnold
- GTC session: AI for Learning Photorealistic 3D Digital Humans from In-the-Wild Data
- NGC Containers: MATLAB
- SDK: Falcor
- SDK: VRWorks Graphics for HMD
About the Authors
