Real-Time On-Device

Deep learning-based

Computer Vision

Nalbi is in the front-line of researching and developing state-of-the-art deep learning-based computer vision proprietary technologies that are highly customized and optimized for embedded systems.

NALBI's

core technologies focus on creating virtual humans on a mobile device in real-time. 

Face Reenactment

Combining the advantages of a 3D engine and Deep-Learning methods, NALBI enables a higher degree of freedom in motion.

3D Motion Capture

Applied 3D mesh to perform full body tracking.

On-Device & Real Time

It can be done on mobile without exorbitant professional equipment.

Reimagine
Everyday Life

Create Your Account - Web3 X Webflow Template

Face Reenactment

Able to express a high degree of freedom in head angle and delicate facial expressions through the 3D engine and Deep-Learning methods. 

ETFs And Stocks - Web3 X Webflow Template

3D Motion Capture

Perform real-time and highly accurate full-body tracking without professional equipment.

Create Your Account - Web3 X Webflow Template

Depth map upsampling

Depth Map Upsampling- Utilizes 4K RGB images and a low-resolution depth map to attain a high-resolution depth map.

ETFs And Stocks - Web3 X Webflow Template

Face&Age Recognition

Face & Age Recognition- Estimates sex and age through face scan on the Cortex-M7 MCU (for device personalization usages).

Real Time Trading - Web3 X Webflow Template

Human segmentation

Separates a human object from the background in real-time from imported images and videos. 

ETFs And Stocks - Web3 X Webflow Template

Depth estimation

Approximates relative depth on a single RGB camera via neural networks. @ARM CPU or Mobile GPU

Currencies And Commodities - Web3 X Webflow Template

Single-RGB Bokeh

Produces a natural bokeh effect with a single RGB image. (Blur Intensity Control and Focus Point function)

Create Your Account - Web3 X Webflow Template

Hair segmentation

Segregates the hair area in real-time. @ARM CPU and dyeing effect @ Mobile GPU (OpenGLE2.0)

Face Detection with Thermal Imaging Camera

Competent in implementing efficient face detection algorithms on the thermal imaging camera without false alarms on high-temperature objects aside from the human facial area.

NALBI
FACENET

Recognizes multiple biological information (face, sex, and age) with a single Deep Learning algorithm model optimized for MCU’s low RAM. 

Image
Segmentation

Separates human objects and background areas effortlessly with a single image on mobile; Capable of natural Bokeh effect production (blur intensity and focus point) Segregates hair, background, human object, and per-instance area.

Single-RGB Bokeh

Produces a natural bokeh effect with a single RGB image. (Blur Intensity Control and Focus Point function)

Hair Segmentation

Segregates the hair area in real-time. @ARM CPU and dyeing effect @ Mobile GPU (OpenGLE2.0)

Human Segmentation

Separates a human object from the background in real-time from imported images and videos

NALBI Newsroom

JOB OPENINGS

Join our team, Make an impact! Let's NALBI!