Related papers: Fast and Memory-Efficient Network Towards Efficien…

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 image to higher resolution. Applications such as gaming…

Deep neural networks (DNN) have demonstrated effectiveness for various applications such as image processing, video segmentation, and speech recognition. Running state-of-the-art DNNs on current systems mostly relies on either…

Single image super-resolution (SR) is an established pixel-level vision task aimed at reconstructing a high-resolution image from its degraded low-resolution counterpart. Despite the notable advancements achieved by leveraging deep neural…

RAW images have shown superior performance than sRGB images in many image processing tasks, especially for low-light image enhancement. However, most existing methods for RAW-based low-light enhancement usually sequentially process…

Convolutional neural network (CNN) has achieved impressive success in computer vision during the past few decades. The image convolution operation helps CNNs to get good performance on image-related tasks. However, it also has high…

Single-image super-resolution (SISR) is an important task in image processing, aiming to enhance the resolution of imaging systems. Recently, SISR has made a significant leap and achieved promising results with deep learning. GAN-based…

Recent advances in neural rendering have shown that, albeit slow, implicit compact models can learn a scene's geometries and view-dependent appearances from multiple views. To maintain such a small memory footprint but achieve faster…

Perceptual Extreme Super-Resolution for single image is extremely difficult, because the texture details of different images vary greatly. To tackle this difficulty, we develop a super resolution network with receptive field block based on…

Real-time semantic segmentation is a challenging task that requires high-accuracy models with low-inference times. Implementing these models on embedded systems is limited by hardware capability and memory usage, which produces bottlenecks.…

Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots. Most semantic segmentation research focuses on improving estimation accuracy with little consideration on efficiency. Several…

We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Thus the running speed can be selected to meet various computational resource limits. Networks trained…

Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results…

Herein, a bit-wise Convolutional Neural Network (CNN) in-memory accelerator is implemented using Spin-Orbit Torque Magnetic Random Access Memory (SOT-MRAM) computational sub-arrays. It utilizes a novel AND-Accumulation method capable of…

Deep neural network training without pre-trained weights and few data is shown to need more training iterations. It is also known that, deeper models are more successful than their shallow counterparts for semantic segmentation task. Thus,…

Single image super-resolution (SISR) is of great importance as a low-level computer vision task. The fast development of Generative Adversarial Network (GAN) based deep learning architectures realises an efficient and effective SISR to…

Deep Convolutional Neural Networks (CNNs), such as Dense Convolutional Networks (DenseNet), have achieved great success for image representation by discovering deep hierarchical information. However, most existing networks simply stacks the…

Image fusion aims to integrate complementary information across modalities to generate high-quality fused images, thereby enhancing the performance of high-level vision tasks. While global spatial modeling mechanisms show promising results,…

Early Exit Neural Networks (EENNs) present a solution to enhance the efficiency of neural network deployments. However, creating EENNs is challenging and requires specialized domain knowledge, due to the large amount of additional design…

In recent years, videos and images in 720p (HD), 1080p (FHD) and 4K (UHD) resolution have become more popular for display devices such as TVs, mobile phones and VR. However, these high resolution images cannot achieve the expected visual…

Scene text image super-resolution (STISR) aims at simultaneously increasing the resolution and readability of low-resolution scene text images, thus boosting the performance of the downstream recognition task. Two factors in scene text…