Ziva Dynamics has officially released a beta for its Real-Time (RT) Face Trainer, an amazing machine-learning-trained, cloud-based facial rigging service for games and real-time work. This Unreal Engine-powered tool essentially transforms any face mesh into a high-performance real-time puppet in one hour. It’s built on a library containing over 15TB of 4D scan data, while the generated face puppets can express over 72,000 training shapes, as well as novel face poses. Read more for a video and additional information.
The Ziva RT face puppets are only 30MB at runtime and run at real-time frame rates (3ms/frame on a single CPU thread). On the technical side of things, a head mesh needs to be cleaned up and retopologised manually to match a standard point order before it can be processed and then subdivided to generate convincing deformations. Unfortunately, ZRT Face Trainer is currently only available on an invite-only basis.
- Aspect Ratio:16:9.Connectivity Technology: HDMI,USB,Ethernet,WiFi,Bluetooth
- Dominate the Game: With the 10th Gen Intel Core i5-10300H processor, your Nitro 5 is packed with incredible power for all your games
- RTX, It's On: The latest NVIDIA GeForce RTX 3050 (4GB dedicated GDDR6 VRAM) is powered by award-winning architecture with new Ray Tracing Cores,...
The ZRT Face Trainer is built on a comprehensive library of 4D data and proprietary machine learning algorithms. Within 1 hour, your character mesh is injected with the game industry’s best tech,” said Ziva Dynamics.