QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms
In this work, we present QuickSRNet, an efficient super-resolution architecture for real-time
applications on mobile platforms. Super-resolution clarifies, sharpens, and upscales an …
applications on mobile platforms. Super-resolution clarifies, sharpens, and upscales an …
Achieving on-mobile real-time super-resolution with neural architecture and pruning search
Though recent years have witnessed remarkable progress in single image super-resolution
(SISR) tasks with the prosperous development of deep neural networks (DNNs), the deep …
(SISR) tasks with the prosperous development of deep neural networks (DNNs), the deep …
Lightweight real-time image super-resolution network for 4k images
G Gankhuyag, K Yoon, J Park… - Proceedings of the …, 2023 - openaccess.thecvf.com
Single-image super-resolution technology has become a topic of extensive research in
various applications, aiming to enhance the quality and resolution of degraded images …
various applications, aiming to enhance the quality and resolution of degraded images …
Overnet: Lightweight multi-scale super-resolution with overscaling network
Super-resolution (SR) has achieved great success due to the development of deep
convolutional neural networks (CNNs). However, as the depth and width of the networks …
convolutional neural networks (CNNs). However, as the depth and width of the networks …
Multi-attention based ultra lightweight image super-resolution
Lightweight image super-resolution (SR) networks have the utmost significance for real-
world applications. There are several deep learning based SR methods with remarkable …
world applications. There are several deep learning based SR methods with remarkable …
Exploring sparsity in image super-resolution for efficient inference
Current CNN-based super-resolution (SR) methods process all locations equally with
computational resources being uniformly assigned in space. However, since missing details …
computational resources being uniformly assigned in space. However, since missing details …
Addersr: Towards energy efficient image super-resolution
This paper studies the single image super-resolution problem using adder neural networks
(AdderNets). Compared with convolutional neural networks, AdderNets utilize additions to …
(AdderNets). Compared with convolutional neural networks, AdderNets utilize additions to …
Dipnet: Efficiency distillation and iterative pruning for image super-resolution
Efficient deep learning-based approaches have achieved remarkable performance in single
image super-resolution. However, recent studies on efficient super-resolution have mainly …
image super-resolution. However, recent studies on efficient super-resolution have mainly …
Bicubic++: Slim, slimmer, slimmest-designing an industry-grade super-resolution network
BB Bilecen, M Ayazoglu - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
We propose a real-time and lightweight single-image super-resolution (SR) network named
Bicubic++. Despite using spatial dimensions of the input image across the whole network …
Bicubic++. Despite using spatial dimensions of the input image across the whole network …
edge-SR: super-resolution for the masses
PN Michelini, Y Lu, X Jiang - Proceedings of the IEEE/CVF …, 2022 - openaccess.thecvf.com
Classic image scaling (eg bicubic) can be seen as one convolutional layer and a single
upscaling filter. Its implementation is ubiquitous in all display devices and image processing …
upscaling filter. Its implementation is ubiquitous in all display devices and image processing …