From the beginning of the 21st century, pilot studies on Machine Learning drew attention to making a machine learn by itself to overcome limitations on high opportunity costs to build logic and data for creating a system.
Research on Deep Learning Technology has come a long way since 2012, and self-learning machines have achieved meaningful results in various fields.
Although different services exist in the Virtual Human industry at present, rapid growth in advanced technology requires higher-level services.
Therefore, a service-based perspective in the field, as well as technological growth, is also essential.
Indeed, NALBI is looking forward to launching a Virtual Human Creation Service that enables anyone to comfortably create a virtual human on mobile devices through real-time 3D Motion Capture technology with accurate movement detection.
NALBI’s model, as the ultimate aggregation of our past seven years of investment in R&D, can dispose of full-body tracking, including natural face, body, and hand movement in real-time, to create high-quality videos without heterogeneity.
Our objective is to maximize the joy of communication by building a compelling connection between people worldwide.
Able to express a high degree of freedom in head angle and delicate facial expressions through the 3D engine and Deep-Learning methods.
3D Motion Capture- Perform real-time and highly accurate full-body tracking without professional equipment.
Depth Map Upsampling- Utilizes 4K RGB images and a low-resolution depth map to attain a high-resolution depth map.
Face & Age Recognition- Estimates sex and age through face scan on the Cortex-M7 MCU (for device personalization usages).
Separates a human object from the background in real-time from imported images and videos.
Approximates relative depth on a single RGB camera via neural networks. @ARM CPU or Mobile GPU
Produces a natural bokeh effect with a single RGB image. (Blur Intensity Control and Focus Point function)
Segregates the hair area in real-time. @ARM CPU and dyeing effect @ Mobile GPU (OpenGLE2.0)