Image and video quality enhancement

Our AI-based algorithms enhance the performance of the embedded camera especially in low-light, higher dynamics, and zooming conditions.



Visidon offers a wide range of algorithms to address complex lighting conditions for embedded cameras in security and surveillance, laptops and webcams, robotics, and drones. Our video noise reduction is a CNN-based model optimized for real-time low-light enhancement and it significantly improves object recognition.

Noise reduction for single images enables capturing a high-quality photo in a dark environment. It utilizes information captured with multiple normally exposed shots and automatically adjusts the image to be clear and sharp with low noise.

Case Study: Real-time denoise solution for edge devices with neural networks



AI-based technology designed for embedded NPU hardware with fast and high-quality video upscale. The algorithm dramatically improves output quality and allows higher zooming levels compared to a basic digital zoom.

Our super resolution technology also allows for creating an upscaled image from multiple low-resolution inputs. This software is especially designed for creating clear and visually great looking zoom images.

Case Study


High Dynamic Range

A solution for correcting and optimizing the dynamic range of photos and videos and enriching the color tone of the output. Combines multiple differently exposed shots and automatically handles moving objects to avoid ghosting or artefacts. Brings hidden details in shadows and highlights visible.



Our frame rate control technology enables the interpolation of movement between shot frames. This increases the frame per second in videos and makes fast movement smoother, as well as allows for slow-motion effects.

Computer vision and

face recognition applications

Our revolutionary computer vision and face recognition SW understands and utilises image data on the go.



Our algorithm can be used for authentication and identification, distinguishing real human faces from photos or video and recognizing their gender, age, and emotion. It is capable of tracking a person’s eyes, nose and mouth, and assessing the person´s drowsiness and distraction.

Case Study - Driver Monitoring



Computes a depth map from single or dual camera inputs. Enables computational bokeh and other stylization effect creation.

Case Study - AI enabled Smart Screen



Identifies faces in view during video calls. Keeps the primary individual in focus and at the center of the frame with face detection and automated adjustment of zoom level or focuses on several meeting room participants and groups them together.