Maybe it’s a silly question, but I’m wondering if it’s possible to use the powerful cpu from the oak for photo enhancement.
Is this somehow possible? I’m actually restoring old black/white photos and would like to use the oak for this.

So this task isn't actually a lot compute extensive, so you could also use the OAK-D as NCS-2 in the mode to do the work. OpenCV offers multiple functions to carry out the work of image brightness enhancement and stuff like that. - https://docs.opencv.org/3.4/d3/dc1/tutorial_basic_linear_transform.html

A bit more info on image enhancement would be really helpful to provide you better links/resources. Are you trying to experiment sort of stuff like Grayscale to RGB conversion?

Thx for your response.
yes, i was thinking about converting black/white to rgb.
actually I’m using a raspberry and a small 10“ mini netbook with the oak. Both computer are too weak for complex projects, so I was thinking about to use the oak for it.

If you use cv::cvtColor(gray, color, cv::COLOR_GRAY2BGR) you should get a 3 channel image but there are no colors, because all the channels have the same value as the gray image.

The area of complete restoration of a Grayscale Image to RGB Image is yet under active reserach and mostly available in research papers, individual author documents etc. This has not yet been officially supported by OpenCV or OpenVINO yet. However, one can enhance the quality and extract meaningful information from a low resolution /blurred image/low contrast using OpenCV. This is possible through here - one can enhance the quality and extract meaningful information from a low resolution /blurred image/low contrast using image processing.

This has not yet been added to Depthai Examples yet, since it is a low power application. Let me know if this was helpful.

Alright, thanks for your explanation. Yes, it is helpful to me.
I must learn a lot in machine learning, especially how to use the oak for my projects. It’s pretty hard for a totally newbie 😉