When there are few photons to capture, then noise is always a problem. Visionary.ai have a new way of using artificial intelligence to remove more noise than other approaches. Image sharpness is retained. For the first time, great images are possible in extremely low lighting conditions, in colour, in real-time.
Conventional approaches to image processors do not use all the available data from an image sensor. The algorithms compress and smooth the image, and there are missed opportunities to use temporal information between successive frames. By using raw Bayer image sensor output data our AI can identify and remove more of the noise.
Visionary.ai understand the computing performance and power constraints of real-world electronic devices. Our denoiser has been developed to run on a choice of cost effective, low power, neural networks at the edge.
Cutting image noise delivers a whole new degree of freedom for system designers. Noise removal could enable to cost and size reduction of image sensors, reduce the energy wasted in illumination, increase the frame rate, or improve the dynamic range.
We know that engineering teams want to be confident in feasibility of a solution before investing their valuable resources.
For a quick, direct comparison, we simply ask that you provide samples of your raw Bayer sensor data, preferably from challenging lighting conditions. We will provide, within one week, a demonstration of the results that our technology can deliver with your current image sensor. We are confident that you will be amazed by the difference.