Related papers: SDAN: Squared Deformable Alignment Network for Lea…

Image segmentation is the foundation of several computer vision tasks, where pixel-wise knowledge is a prerequisite for achieving the desired target. Deep learning has shown promising performance in supervised image segmentation. However,…

In the field of multimedia, single image deraining is a basic pre-processing work, which can greatly improve the visual effect of subsequent high-level tasks in rainy conditions. In this paper, we propose an effective algorithm, called…

Visual odometry (VO) and SLAM have been using multi-view geometry via local structure from motion for decades. These methods have a slight disadvantage in challenging scenarios such as low-texture images, dynamic scenarios, etc. Meanwhile,…

Images degraded by geometric distortions pose a significant challenge to imaging and computer vision tasks such as object recognition. Deep learning-based imaging models usually fail to give accurate performance for geometrically distorted…

Defect detection is a basic and essential task in automatic parts production, especially for automotive engine precision parts. In this paper, we propose a new idea to construct a deep convolutional network combining related knowledge of…

This paper presents a deep learning approach for the classification of Engineering (CAD) models using Convolutional Neural Networks (CNNs). Owing to the availability of large annotated datasets and also enough computational power in the…

Lighting estimation from face images is an important task and has applications in many areas such as image editing, intrinsic image decomposition, and image forgery detection. We propose to train a deep Convolutional Neural Network (CNN) to…

This paper considers the problem of reconstructing an object with high-resolution using several low-resolution images, which are degraded due to nonuniform defocus effects caused by angular misalignment of the subpixel motions. The new…

Recent RGB-D semantic segmentation has motivated research interest thanks to the accessibility of complementary modalities from the input side. Existing works often adopt a two-stream architecture that processes photometric and geometric…

Super-resolution of LiDAR range images is crucial to improving many downstream tasks such as object detection, recognition, and tracking. While deep learning has made a remarkable advances in super-resolution techniques, typical…

Convolutional Neural Networks (CNNs) are the predominant model used for a variety of medical image analysis tasks. At inference time, these models are computationally intensive, especially with volumetric data. In principle, it is possible…

Recent promising effort for spectral reconstruction (SR) focuses on learning a complicated mapping through using a deeper and wider convolutional neural networks (CNNs). Nevertheless, most CNN-based SR algorithms neglect to explore the…

In this article, we present SWAN: a three-stage, self-supervised wavelet neural network for joint estimation of endmembers and abundances from hyperspectral imagery. The contiguous and overlapping hyperspectral band images are first…

Recently, deep neural networks (DNNs) have shown advantages in accelerating optimization algorithms. One approach is to unfold finite number of iterations of conventional optimization algorithms and to learn parameters in the algorithms.…

Most of current display devices are with eight or higher bit-depth. However, the quality of most multimedia tools cannot achieve this bit-depth standard for the generating images. De-quantization can improve the visual quality of low…

This paper introduces Quaternion Approximate Networks (QUAN), a novel deep learning framework that leverages quaternion algebra for rotation equivariant image classification and object detection. Unlike conventional quaternion neural…

Modern Convolutional Neural Networks (CNN) are extremely powerful on a range of computer vision tasks. However, their performance may degrade when the data is characterised by large intra-class variability caused by spatial transformations.…

Zero-Shot Learning (ZSL) seeks to recognize a sample from either seen or unseen domain by projecting the image data and semantic labels into a joint embedding space. However, most existing methods directly adapt a well-trained projection…

An approach to incorporate deep learning within an iterative image reconstruction framework to reconstruct images from severely incomplete measurement data is presented. Specifically, we utilize a convolutional neural network (CNN) as a…

We propose DeepMapping, a novel registration framework using deep neural networks (DNNs) as auxiliary functions to align multiple point clouds from scratch to a globally consistent frame. We use DNNs to model the highly non-convex mapping…