Synthesis AI Releases New Products for Human-Centric Computer Vision Models

Synthesis AI, a leading company in synthetic data technologies, has announced the release of two new products for the development of advanced human-centric computer vision models. The two products, called Synthesis Humans and Synthesis Scenarios, are powered by generative AI and cinematic computer graphics technologies and enable the simulation of complex multi-human data. 

According to the company, the new products are an extension of the company’s existing data generation platform. They were designed to make the creation and implementation of synthetic data easier and more accessible. 

Yashar Behzadi is CEO and Founder of Synthesis AI. 

“Synthesis Humans and Synthesis Scenarios are a natural evolution in our synthetic data roadmap,” Behzadi said. “Synthetic data powered by generative AI is now recognized as a more efficient paradigm for building computer vision AI. Our new products will enable the development of more sophisticated multi-human AI models essential for emerging applications.” 

Synthesis Humans and Synthesis Scenarios Capabilities 

Through the use of Synthesis Humans, machine learning developers can construct sophisticated production-scale models. The product provides more than 100,000 unique identifiers and offers practitioners the ability to modify various attributes like emotion, body type, and motion. The user interface enables them to seamlessly create labeled data, and the comprehensive API can be used by teams that prefer programmatic access and control. 

The other main product, Synthesis Scenarios, is the first of its kind to allow the fine control of complex, multi-human simulations across a wide range of environments for machine learning model development. Various companies involved with augmented reality (AR), virtual reality (VR), autonomy and more rely on the platform to build efficient and robust models. 

Supporting Wider Range of Applications

The new products mean Synthesis AI now supports machine learning model development for a wider range of existing and emerging applications, such as ID verification, AR/VR, metaverse, virtual try-on, AI fitness, driver and passenger monitoring, teleconferencing, pedestrian detection, VFX, security, and more. 

For example, a company involved with ID verification could use Synthesis Humans to access diverse data that is privacy compliant, which helps mitigate the privacy and regulatory constraints of obtaining facial data. When it comes to AR, VR, and the metaverse, Synthesis Humans can be used to obtain labeled 3D data across a wide range of demographics, while Synthesis Scenarios supports the development of multi-person tracking and interaction models. 

These are just a few of the many potential applications of the two products. 

Florian Leibert of 468 Capital had this to say about the company and its offerings: 

“Synthesis AI continues to innovate in synthetic data. The company’s platform is the first to bring generative AI together with computer graphics pipelines, helping their customers create photorealistic, diverse and perfectly labeled training data. The new products represent a significant advancement, enabling computer vision teams to build ML models more cost-effectively across more applications and industries.” 

The two new products will be available starting this month (November 2022).