Perceptual-Centric Image Super-Resolution using Heterogeneous Processors on Mobile Devices
Image super-resolution (SR) is widely used on mobile devices to enhance user experience.
However, neural networks used for SR are computationally expensive, posing challenges …
However, neural networks used for SR are computationally expensive, posing challenges …
Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded Devices
Deep neural network (DNN) inference is increasingly being executed on mobile and
embedded platforms due to several key advantages in latency, privacy and always-on …
embedded platforms due to several key advantages in latency, privacy and always-on …
[PDF][PDF] TileSR: Accelerate On-Device Super-Resolution with Parallel Offloading in Tile Granularity
Recent years have witnessed the unprecedented performance of convolutional networks in
image super-resolution (SR). SR involves upscaling a single low-resolution image to meet …
image super-resolution (SR). SR involves upscaling a single low-resolution image to meet …
Multimedia service distribution platform in edge computing environments
J Park - 2024 IEEE International Symposium on Broadband …, 2024 - ieeexplore.ieee.org
In this paper, we design and develop a new multimedia distribution platform that mainly
utilizes containerization and microservice architecture technologies. Using our approach …
utilizes containerization and microservice architecture technologies. Using our approach …