Super Resolution
Super resolution is a process that uses AI algorithms to create a higher-resolution version of an image or video from a lower-resolution input by intelligently adding detail, rather than just simply enlarging pixels.
It increases the pixel count and enhances image sharpness and clarity, making it useful for preparing images for large prints, improving the quality of older or lower-resolution photos, and producing clearer, more detailed image
In the example, I’ve taken a 48×48 image and increased its resolution to 192×192. I can use the CPU, GPU or NPU to perform the process. Let’s use the NPU.
I’ve taken a 48×48 image and scaled it by a factor of 4.
There are a few models available: sr_1033 is the default, but there’s also sr_1032, and esrgan available.
Semantic Segmentation
This plugin performs semantic segmentation on the current layer. Semantic segmentation is a computer vision task that assigns a class label to pixels using a deep learning (DL) algorithm.
The plugin lets you use either the deeplabv3 model or the sseg-adas-0001 model. The process can run on the CPU, GPU, or NPU (providing you installed the intel-npu-driver).
I hope this article has given a taster of what the plugins can do running on an iGPU.
Pages in this article:
Page 1 – Introduction
Page 2 – Stable Diffusion
Page 3 – Semantic Segmentation, Super Resolution
Complete list of articles in this series:
| ASRock Industrial NUC BOX-255H | |
|---|---|
| Introduction | Introduction to the series and interrogation of the NUC BOX-255H |
| Benchmarks | Benchmarking the NUC BOX-255H |
| Power | Testing and comparing the power consumption under various workloads |
| Stable Diffusion | Deep Learning with Stable Diffusion |
| Audacity AI Plugins | Let's explore OpenVINO AI Plugins for Audacity |
| 3 Types of Cores | P-cores, E-cores and low power E-cores performance |
| GIMP AI Plugins | Stable Diffusion, Super Resolution, Semantic Segmentation |