Sliding spotlight mode is widely used in spaceborne SAR to achieve high resolution. However, due to the difficulty for antenna beam to scan continuously, it usually works by step scanning, which leads to paired-echo i...
详细信息
Single image super-resolution (SISR) aims to recover the high-resolution (HR) image from its low-resolution (LR) input image. With the development of deep learning, SISR has achieved great progress. However, It is sti...
详细信息
Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task. To alleviate this problem, we raise t...
详细信息
Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving three-dimensional reconstruction along the elevation direction from multiple observations. In recent y...
详细信息
Asymmetric retrieval systems, characterized by the deployment of models with varying capacities on platforms with differing computational and storage resources, pose a challenge in balancing retrieval efficiency and a...
详细信息
Video coding is a mathematical optimization problem of rate and distortion essentially. To solve this complex optimization problem in practice, two popular video coding frameworks have been developed: block-based hybr...
详细信息
Video coding is a mathematical optimization problem of rate and distortion essentially. To solve this complex optimization problem in practice, two popular video coding frameworks have been developed: block-based hybrid video coding and end-to-end learned video coding. If we rethink video coding from the perspective of optimization, we find that the existing two frameworks represent two directions of optimization solutions. Block-based hybrid video coding represents the discrete optimization solution because those irrelevant coding modes are discrete in mathematics. The discrete solution provides multiple starting points (i.e. modes) in global optimization space and then searches for the best one among them. However, the search-based optimization algorithm is not efficient enough. On the other hand, end-to-end learned video coding represents the continuous optimization solution because the optimization algorithm of deep learning, gradient descent, is based on a continuous function. The continuous solution optimizes a group of model parameters efficiently by such a numerical algorithm. However, limited by only one starting point, it is easy to fall into the local optimum. To better solve the optimization problem, we propose a hybrid of discrete and continuous optimization video coding. We regard video coding as a hybrid of the discrete and continuous optimization problem, and use both search and numerical algorithm to solve it. Our idea is to provide multiple discrete starting points in the global space and optimize the local optimum around each point by numerical algorithm efficiently. Finally, we search for the global optimum among those local optimums. Guided by the hybrid optimization idea, we design a hybrid optimization video coding framework, which is built on continuous deep networks entirely and also contains some discrete modes. We conduct a comprehensive set of experiments to verify the efficiency of our hybrid optimization. Compared to the continuous opti
Synthetic aperture radar (SAR) tomography (TomoSAR) retrieves three-dimensional (3-D) information from multiple SAR images, effectively addresses the layover problem, and has become pivotal in urban mapping. Unmanned ...
详细信息
Few-shot image generation aims to train generative models using a small number of training images. When there are few images available for training (e.g. 10 images), Learning From Scratch (LFS) methods often generate ...
详细信息
Learning-based image deraining methods have achieved remarkable success in the past few decades. Currently, most deraining architectures are developed by human experts, which is a laborious and error-prone process. In...
详细信息
ISBN:
(纸本)9781728173221
Learning-based image deraining methods have achieved remarkable success in the past few decades. Currently, most deraining architectures are developed by human experts, which is a laborious and error-prone process. In this paper, we present a study on employing neural architecture search (NAS) to automatically design deraining architectures, dubbed AutoDerain. Specifically, we first propose an U-shaped deraining architecture, which mainly consists of residual squeeze-and-excitation blocks (RSEBs). Then, we define a search space, where we search for the convolutional types and the use of the squeeze-and-excitation block. Considering that the differentiable architecture search is memory-intensive, we propose a memory-efficient differentiable architecture search scheme (MDARTS). In light of the success of training binary neural networks, MDARTS optimizes architecture parameters through the proximal gradient, which only consumes the same GPU memory as training a single deraining model. Experimental results demonstrate that the architecture designed by MDARTS is superior to manually designed derainers.
Image quality assessment (IQA) aims to estimate human perception based image visual quality. Although existing deep neural networks (DNNs) have shown significant effectiveness for tackling the IQA problem, it still ne...
详细信息
Image quality assessment (IQA) aims to estimate human perception based image visual quality. Although existing deep neural networks (DNNs) have shown significant effectiveness for tackling the IQA problem, it still needs to improve the DNN-based quality assessment models by exploiting efficient multi-scale features. In this paper, motivated by the human visual system (HVS) combining multi-scale features for perception, we propose to use pyramid features learning to build a DNN with hierarchical multi-scale features for distorted image quality prediction. Our model is based on both residual maps and distorted images in luminance domain, where the proposed network contains spatial pyramid pooling and feature pyramid from the network structure. Our proposed network is optimized in a deep end-to-end supervision manner. To validate the effectiveness of the proposed method, extensive experiments are conducted on four widely-used image quality assessment databases, demonstrating the superiority of our algorithm.
暂无评论