Related papers: AdaBM: On-the-Fly Adaptive Bit Mapping for Image S…
Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and performance. Residual binarization enables hardware-friendly, matmul-free inference by stacking…
With the rising popularity of intelligent mobile devices, it is of great practical significance to develop accurate, realtime and energy-efficient image Super-Resolution (SR) inference methods. A prevailing method for improving the…
Small animal PET scanners require high spatial resolution and good sensitivity. To reconstruct high-resolution images in 3D-PET, iterative methods, such as OSEM, are superior to analytical reconstruction algorithms, although their high…
Video super-resolution reconstruction (SRR) algorithms attempt to reconstruct high-resolution (HR) video sequences from low-resolution observations. Although recent progress in video SRR has significantly improved the quality of the…
This paper studies the Binary Neural Networks (BNNs) in which weights and activations are both binarized into 1-bit values, thus greatly reducing the memory usage and computational complexity. Since the modern deep neural networks are of…
In this paper, we introduce Saliency-Based Adaptive Masking (SBAM), a novel and cost-effective approach that significantly enhances the pre-training performance of Masked Image Modeling (MIM) approaches by prioritizing token salience. Our…
Recently, deep learning based single image super-resolution(SR) approaches have achieved great development. The state-of-the-art SR methods usually adopt a feed-forward pipeline to establish a non-linear mapping between low-res(LR) and…
We introduce a new algorithm to solve a regularized spatial-spectral image estimation problem. Our approach is based on the linearized alternating directions method of multipliers (LADMM), which is a variation of the popular ADMM algorithm.…
State-Space Models (SSMs) have attracted considerable attention in Image Restoration (IR) due to their ability to scale linearly sequence length while effectively capturing long-distance dependencies. However, deploying SSMs to edge devices…
Recent convolutional neural network (CNN) development continues to advance the state-of-the-art model accuracy for various applications. However, the enhanced accuracy comes at the cost of substantial memory bandwidth and storage…
State-of-the-art super-resolution (SR) algorithms require significant computational resources to achieve real-time throughput (e.g., 60Mpixels/s for HD video). This paper introduces FAST (Free Adaptive Super-resolution via Transfer), a…
With the development of hardware for machine learning, newer models often come at the cost of both increased sizes and computational complexity. In effort to improve the efficiency for these models, we apply and investigate recent…
Motion estimation is the most critical process in video coding systems. First of all, it has a definitive impact on the rate-distortion performance given by the video encoder. Secondly, it is the most computationally intensive process…
In recent years Deep Neural Networks (DNNs) have been rapidly developed in various applications, together with increasingly complex architectures. The performance gain of these DNNs generally comes with high computational costs and large…
Adaptive block-based compressive sensing (ABCS) algorithms are studied in the context of the practical realization of compressive sensing on resource-constrained image and video sensing platforms that use single-pixel cameras, multi-pixel…
We address the problem of estimating a high quality dense depth map from a single RGB input image. We start out with a baseline encoder-decoder convolutional neural network architecture and pose the question of how the global processing of…
Large Language Models (LLMs) have revolutionized natural language processing tasks. However, their practical application is constrained by substantial memory and computational demands. Post-training quantization (PTQ) is considered an…
Deep convolutional neural networks (DCNNs) have recently demonstrated high-quality results in single-image super-resolution (SR). DCNNs often suffer from over-parametrization and large amounts of redundancy, which results in inefficient…
Neural Radiance Fields (NeRF) offer significant promise for generating photorealistic images and videos. However, existing mainstream neural rendering models often fall short in meeting the demands for immediacy and power efficiency in…
Deep learning has been successfully applied to the single-image super-resolution (SISR) task with great performance in recent years. However, most convolutional neural network based SR models require heavy computation, which limit their…