Accelerate Background Blur and Low-Light Camera Effects
Introduction
Prerequisites
Overview
Build the pipelines
Run the pipelines
Performance
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

KleidiAI

KleidiAI is an open-source library that provides optimized, performance-critical routines - also known as micro-kernels - for artificial intelligence (AI) workloads on Arm CPUs.

These routines are tuned to take full advantage of specific Arm hardware architectures to maximize performance. The KleidiAI library is designed for easy integration into C or C++ machine learning (ML) and AI frameworks.

Several popular AI frameworks already take advantage of KleidiAI to improve performance on Arm platforms.

KleidiCV

KleidiCV is an open-source library that provides high-performance image processing functions for AArch64.

It is designed to be lightweight and simple to integrate into a wide variety of projects. Some computer vision frameworks, such as OpenCV, leverage KleidiCV to accelerate image processing on Arm devices.

AI camera pipelines

This Learning Path provides two example applications that combine AI and computer vision (CV) techniques:

  • Background Blur.
  • Low-Light Enhancement.

Both applications:

  • Use input and output images that are stored in ppm (Portable Pixmap format), with three RGB channels (Red, Green, and Blue). Each channel supports 256 intensity levels (0-255) commonly referred to as RGB8.
  • Convert the images to the YUV420 color space for processing.
  • Apply the relevant effect (background blur or low-light enhancement).
  • Convert the processed images back to RGB8 and save them as ppm files.

Background Blur

The background blur pipeline is implemented as follows:

Image Alt Text:example image alt-textBackground Blur Pipeline Diagram

Low Light Enhancement

The low-light enhancement pipeline is adapted from the LiveHDR+ method originally proposed by Google Research in 2017:

Image Alt Text:example image alt-textLow-Light Enhancement Pipeline Diagram

The Low-Resolution Coefficient Prediction Network (implemented with TFLite) performs computations such as:

  • Strided convolutions.
  • Local feature extraction using convolutional layers.
  • Global feature extraction using convolutional and fully connected layers.
  • Add, convolve, and reshape operations.
Back
Next