基于监督学习的单幅图像深度估计综述

单幅图像深度估计是三维重建中基于图像获取场景深度的重要技术,也是计算机视觉中的经典问题,近年来,基于监督学习的单幅图像深度估计发展迅速.文中介绍了基于监督学习的单幅图像深度估计及其模型和优化方法;分析了现有的参数学习、非参数学习、深度学习3类方法及每类方法的国内外研究现状及优缺点;最后对基于监督学习的单幅图像深度估计进行总结,得出了深度学习框架下的单幅图像深度估计是未来研究的发展趋势和重点.     

深度学习背景下的图像三维重建技术进展综述

三维重建是指从单幅或多幅二维图像中重建出物体的三维模型并对三维模型进行纹理映射的过程。三维重建可获取从任意视角观测并具有色彩纹理的三维模型,是计算机视觉领域的一个重要研究方向。传统的三维重建方法通常需要输入大量图像,并进行相机参数估计、密集点云重建、表面重建和纹理映射等多个步骤。近年来,深度学习背景下的图像三维重建受到了广泛关注,并表现出了优越的性能和发展前景。本文对深度学习背景下的图像三维重建的技术方法、评测方法和数据集进行全面综述。首先对三维重建进行分类,根据三维模型的表示形式可将图像三维重建方法分类为基于体素的三维重建、基于点云的三维重建和基于网格的三维重建;根据输入图像的类型可将图像三维重建分类为单幅图像三维重建和多幅图像三维重建。随后介绍了不同类别的三维重建方法,从三维重建方法的输入、三维模型表示形式、模型纹理颜色、重建网络的基准值类型和特点等方面进行总结,归纳了深度学习背景下的图像三维重建方法的常用数据集和实验对比,最后总结了当前图像三维重建领域的待解决问题以及未来的研究方向。     

基于深度学习的单幅图像超分辨率重建算法综述

单幅图像超分辨率(Single image super-resolution, SISR)重建是计算机视觉领域上的一个重要问题, 在安防视频监控、飞机航拍以及卫星遥感等方面具有重要的研究意义和应用价值. 近年来, 深度学习在图像分类、检测、识别等诸多领域中取得了突破性进展, 也推动着图像超分辨率重建技术的发展. 本文首先介绍单幅图像超分辨率重建的常用公共图像数据集; 然后, 重点阐述基于深度学习的单幅图像超分辨率重建方向的创新与进展; 最后, 讨论了单幅图像超分辨率重建方向上存在的困难和挑战, 并对未来的发展趋势进行了思考与展望.     

基于深度学习的单幅图片超分辨率重构研究进展

图像超分辨率重构技术是一种以一幅或同一场景中的多幅低分辨率图像为输入, 结合图像的先验知识重构出一幅高分辨率图像的技术. 这一技术能够在不改变现有硬件设备的前提下, 有效提高图像分辨率. 深度学习近年来在图像领域发展迅猛, 它的引入为单幅图片超分辨率重构带来了新的发展前景. 本文主要对当前基于深度学习的单幅图片超分辨率重构方法的研究现状和发展趋势进行总结梳理: 首先根据不同的网络基础对十几种基于深度学习的单幅图片超分辨率重构的网络模型进行分类介绍, 分析这些模型在网络结构、输入信息、损失函数、放大因子以及评价指标等方面的差异; 然后给出它们的实验结果, 并对实验结果及存在的问题进行总结与分析; 最后给出基于深度学习的单幅图片超分辨率重构方法的未来发展方向和存在的挑战.     

深度学习的单幅图像超分辨率重建方法综述

图像超分辨率重建即使用特定算法将同一场景中的低分辨率模糊图像恢复成高分辨率图像。近年来,随着深度学习的蓬勃发展,该技术在很多领域都得到了广泛的应用,在图像超分辨率重建领域中基于深度学习的方法被研究的越来越多。为了掌握当前基于深度学习的图像超分辨率重建算法的发展状况和研究趋势,对目前图像超分辨率的流行算法进行综述。主要从现有单幅图像超分辨算法的网络模型结构、尺度放大方法和损失函数三个方面进行详细论述,分析各类方法的缺陷和益处,同时通过实验对比分析不同网络模型、不同损失函数在主流数据集上的重建效果,最后展望基于深度学习的单幅图像超分辨重建算法未来的发展方向。     

基于KINECT FUSION的室内目标三维重建系统

三维重建是计算机科学领域研究的热点,从一门尖端且难以摸索的学科到逐步与大众市场接轨,三维重建技术渐渐地融入到人们的工作、学习和生活当中。以微软公司推出的Kinect传感器为代表的深度图像采集设备被普遍采用到三维重建领域,基于Kinect Fusion的三维重建技术在该领域得到了广泛的应用。Kinect Fusion是一种操作简便、速度较快且成本低廉的三维重建方法,使用Kinect传感器作为采集深度图像的输入设备,经过对原始深度图像的去噪、平滑以及表面重建等一系列方法,最终可以获得目标物体在三维空间中的点云模型。     

深度学习单目深度估计研究进展

单目深度估计是从单幅图像中获取场景深度信息的重要技术,在智能汽车和机器人定位等领域应用广泛,具有重要的研究价值。随着深度学习技术的发展,涌现出许多基于深度学习的单目深度估计研究,单目深度估计性能也取得了很大进展。本文按照单目深度估计模型采用的训练数据的类型,从3个方面综述了近年来基于深度学习的单目深度估计方法：基于单图像训练的模型、基于多图像训练的模型和基于辅助信息优化训练的单目深度估计模型。同时,本文在综述了单目深度估计研究常用数据集和性能指标基础上,对经典的单目深度估计模型进行了性能比较分析。以单幅图像作为训练数据的模型具有网络结构简单的特点,但泛化性能较差。采用多图像训练的深度估计网络有更强的泛化性,但网络的参数量大、网络收敛速度慢、训练耗时长。引入辅助信息的深度估计网络的深度估计精度得到了进一步提升,但辅助信息的引入会造成网络结构复杂、收敛速度慢等问题。单目深度估计研究还存在许多的难题和挑战。利用多图像输入中包含的潜在信息和特定领域的约束信息,来提高单目深度估计的性能,逐渐成为了单目深度估计研究的趋势。     

深度学习在高光谱图像分类领域的研究现状与展望

高光谱图像（Hyperspectral imagery,HSI）分类是高光谱遥感对地观测技术的一项重要内容,在军事及民用领域都有着重要的应用.然而,高光谱图像的高维特性、波段间高度相关性、光谱混合等使得高光谱图像分类面临巨大挑战.近年来,随着深度学习新技术的出现,基于深度学习的高光谱图像分类在方法和性能上得到了突破性的进展,为其研究提供了新的契机.本文首先介绍了高光谱图像分类的背景、研究现状及几个常用的数据集,并简要概述了几种典型的深度学习模型,最后详细介绍了当前的一些基于深度学习的高光谱图像分类方法,总结了深度学习在高光谱图像分类领域中的主要作用和存在的问题,并对未来的研究方向进行了展望.     

基于深度学习的单幅图像超分辨率重建综述

单幅图像超分辨率SISR重建指从单幅低分辨率图像恢复出高分辨率图像。深度学习方法越来越多地用于图像超分辨重建领域,由于深度网络模型可以自主学习低分辨率图像到高分辨率图像之间的映射关系,与传统方法相比在该领域展现出了更好的重建效果,因而 基于深度学习的方法已经成为目前图像超分辨率重建领域的主流方向。围绕现有的超分辨深度网络模型在重建方式、结构组成和损失函数方面展开的探索进行了综合论述,通过比较不同模型之间存在的异同点,分析了不同的模型构建方法存在的优缺点及适应的应用场景,同时比较不同网络模型在主流测试数据集上的重建效果,并对该领域的未来研究方向进行了展望。     

深度学习在手写汉字识别中的应用综述

手写汉字识别（Handwritten Chinese character recognition,HCCR）是模式识别的一个重要研究领域,最近几十年来得到了广泛的研究与关注,随着深度学习新技术的出现,近年来基于深度学习的手写汉字识别在方法和性能上得到了突破性的进展.本文综述了深度学习在手写汉字识别领域的研究进展及具体应用.首先介绍了手写汉字识别的研究背景与现状.其次简要概述了深度学习的几种典型结构模型并介绍了一些主流的开源工具,在此基础上详细综述了基于深度学习的联机和脱机手写汉字识别的方法,阐述了相关方法的原理、技术细节、性能指标等现状情况,最后进行了分析与总结,指出了手写汉字识别领域仍需要解决的问题及未来的研究方向.     

Learning stratified 3D reconstruction

Stratified 3D reconstruction, or a layer-by-layer 3D reconstruction upgraded from projective to affine, then to the final metric reconstruction, is a well-known 3D reconstruction method in computer vision. It is also a key supporting technology for various well-known applications, such as streetview, smart3D, oblique photogrammetry. Generally speaking, the existing computer vision methods in the literature can be roughly classified into either the geometry-based approaches for spatial vision or the learning-based approaches for object vision. Although deep learning has demonstrated tremendous success in object vision in recent years, learning 3D scene reconstruction from multiple images is still rare, even not existent, except for those on depth learning from single images. This study is to explore the feasibility of learning the stratified 3D reconstruction from putative point correspondences across images, and to assess whether it could also be as robust to matching outliers as the traditional geometry-based methods do. In this study, a special parsimonious neural network is designed for the learning. Our results show that it is indeed possible to learn a stratified 3D reconstruction from noisy image point correspondences, and the learnt reconstruction results appear satisfactory although they are still not on a par with the state-of-the-arts in the structure-from-motion community due to largely its lack of an explicit robust outlier detector such as random sample consensus (RANSAC). To the best of our knowledge, our study is the first attempt in the literature to learn 3D scene reconstruction from multiple images. Our results also show that how to implicitly or explicitly integrate an outlier detector in learning methods is a key problem to solve in order to learn comparable 3D scene structures to those by the current geometry-based state-of-the-arts. Otherwise any significant advancement of learning 3D structures from multiple images seems difficult, if not impossible. Besides, we even speculate that deep learning might be, in nature, not suitable for learning 3D structure from multiple images, or more generally, for solving spatial vision problems.     

大规模室外图像3维重建技术研究进展

基于图像的3维重建旨在从一组2维多视角图像中精确地恢复真实场景的几何形状,是计算机视觉和摄影测量中基础且活跃的研究课题,具有重要的理论研究意义和应用价值,在智慧城市、虚拟旅游、数字遗产保护、数字地图和导航等领域有着广泛应用。随着图像采集系统（智能手机、消费级数码相机和民用无人机等）的普及和互联网的高速发展,通过搜索引擎可以获取大量关于某个室外场景的互联网图像。利用这些图像进行高效鲁棒准确的3维重建,为用户提供真实感知和沉浸式体验已经成为研究热点,引发了学术界和产业界的广泛关注,涌现了多种方法。深度学习的出现为大规模室外图像的3维重建提供了新的契机。首先阐述大规模室外图像3维重建的基本串行过程,包括图像检索、图像特征点匹配、运动恢复结构和多视图立体。然后从传统方法和基于深度学习的方法两个角度,分别系统全面地回顾大规模室外图像3维重建技术在各重建子过程中的发展和应用,总结各子过程中适用于大规模室外场景的数据集和评价指标。最后介绍现有主流的开源和商业3维重建系统以及国内相关产业的发展现状。     

3D-CDRNet: Retrieval-based dense point cloud reconstruction from a single image under complex background

3D reconstruction technique based on deep learning is gaining increasing attention from researchers. The majority of current 3D reconstruction techniques require a simple background, which limit their applications on complex background image. Extracting point cloud features comprehensively is also extremely difficult. This paper design a novel 3D reconstruction network to overcome these limitations. Firstly, we get the image and the retrieved point cloud that is the most similar to the input image. Secondly, to learn the features of the retrieved point cloud, the network encodes and decodes the single image and the retrieved point cloud to generate sparse point cloud. Finally, the proposed dense module densifies the sparse point cloud into the dense point cloud. We use single image of complex background and public dataset to evaluate our network. The reconstruction results indicate that the network surpasses previous reconstruction networks.     

基于深度学习的三维数据分析理解方法研究综述

基于深度学习的三维数据分析理解是数字几何领域的一个研究热点.不同于基于深度学习的图像分析理解,基于深度学习的三维数据分析理解需要解决的首要问题是数据表达的多样性.相较于规则的二维图像,三维数据有离散表达和连续表达的方法,目前基于深度学习的相关工作多基于三维数据的离散表示,不同的三维数据表达方法与不同的数字几何处理任务对深度学习网络的要求也不同.本文首先汇总了常用的三维数据集与特定任务的评价指标,并分析了三维模型特征描述符.然后从特定任务出发,就不同的三维数据表达方式,对现有的基于深度学习的三维数据分析理解网络进行综述,对各类方法进行对比分析,并从三维数据表达方法的角度进一步汇总现有工作.最后基于国内外研究现状,讨论了亟待解决的挑战性问题,展望了未来发展的趋势.     

Deep reinforcement learning in computer vision: a comprehensive survey

Deep reinforcement learning augments the reinforcement learning framework and utilizes the powerful representation of deep neural networks. Recent works have demonstrated the remarkable successes of deep reinforcement learning in various domains including finance, medicine, healthcare, video games, robotics, and computer vision. In this work, we provide a detailed review of recent and state-of-the-art research advances of deep reinforcement learning in computer vision. We start with comprehending the theories of deep learning, reinforcement learning, and deep reinforcement learning. We then propose a categorization of deep reinforcement learning methodologies and discuss their advantages and limitations. In particular, we divide deep reinforcement learning into seven main categories according to their applications in computer vision, i.e. (i) landmark localization (ii) object detection; (iii) object tracking; (iv) registration on both 2D image and 3D image volumetric data (v) image segmentation; (vi) videos analysis; and (vii) other applications. Each of these categories is further analyzed with reinforcement learning techniques, network design, and performance. Moreover, we provide a comprehensive analysis of the existing publicly available datasets and examine source code availability. Finally, we present some open issues and discuss future research directions on deep reinforcement learning in computer vision.

     

深度学习在目标视觉检测中的应用进展与展望

目标视觉检测是计算机视觉领域的一个重要问题,在视频监控、自主驾驶、人机交互等方面具有重要的研究意义和应用价值.近年来,深度学习在图像分类研究中取得了突破性进展,也带动着目标视觉检测取得突飞猛进的发展.本文综述了深度学习在目标视觉检测中的应用进展与展望.首先对目标视觉检测的基本流程进行总结,并介绍了目标视觉检测研究常用的公共数据集;然后重点介绍了目前发展迅猛的深度学习方法在目标视觉检测中的最新应用进展;最后讨论了深度学习方法应用于目标视觉检测时存在的困难和挑战,并对今后的发展趋势进行展望.     

Image fusion meets deep learning: A survey and perspective

Image fusion, which refers to extracting and then combining the most meaningful information from different source images, aims to generate a single image that is more informative and beneficial for subsequent applications. The development of deep learning has promoted tremendous progress in image fusion, and the powerful feature extraction and reconstruction capabilities of neural networks make the fused results promising. Recently, several latest deep learning technologies have made image fusion explode, e.g., generative adversarial networks, autoencoder, etc. However, a comprehensive review and analysis of latest deep-learning methods in different fusion scenarios is lacking. To this end and in this survey, we first introduce the concept of image fusion, and classify the methods from the perspectives of the deep architectures adopted and fusion scenarios. Then, we review the state-of-the-art on the use of deep learning in various types of image fusion scenarios, including the digital photography image fusion, the multi-modal image fusion and the sharpening fusion. Subsequently, the evaluation for some representative methods in specific fusion tasks are performed qualitatively and quantitatively. Moreover, we briefly introduce several typical applications of image fusion, including photography visualization, RGBT object tracking, medical diagnosis, and remote sensing monitoring. Finally, we provide the conclusion, highlight the challenges in image fusion, and look forward to potential future research directions.     

Object detection,shape recovery,and 3D modelling by depth-encoded hough voting

Detecting objects, estimating their pose, and recovering their 3D shape are critical problems in many vision and robotics applications. This paper addresses the above needs using a two stages approach. In the first stage, we propose a new method called DEHV – Depth-Encoded Hough Voting. DEHV jointly detects objects, infers their categories, estimates their pose, and infers/decodes objects depth maps from either a single image (when no depth maps are available in testing) or a single image augmented with depth map (when this is available in testing). Inspired by the Hough voting scheme introduced in [1], DEHV incorporates depth information into the process of learning distributions of image features (patches) representing an object category. DEHV takes advantage of the interplay between the scale of each object patch in the image and its distance (depth) from the corresponding physical patch attached to the 3D object. Once the depth map is given, a full reconstruction is achieved in a second (3D modelling) stage, where modified or state-of-the-art 3D shape and texture completion techniques are used to recover the complete 3D model. Extensive quantitative and qualitative experimental analysis on existing datasets [2], [3], [4] and a newly proposed 3D table-top object category dataset shows that our DEHV scheme obtains competitive detection and pose estimation results. Finally, the quality of 3D modelling in terms of both shape completion and texture completion is evaluated on a 3D modelling dataset containing both in-door and out-door object categories. We demonstrate that our overall algorithm can obtain convincing 3D shape reconstruction from just one single uncalibrated image.     

基于轻量自动残差缩放网络的图像超分辨率重建

近年来,由于深度卷积神经网络的出色性能,深度学习已成为图像超分辨率领域的研究热点,已经有许多具有很深结构的大型模型被提出。而在实际应用中,普通个人计算机或智能终端的硬件显然不适合大规模深度神经网络模型。提出了一种针对单幅图像超分辨率且具有自动残差缩放功能的轻量级网络(ARSN),与许多基于深度学习的方法相比,它的层和参数更少。此外,该网络中有特殊的残差块和跳跃连接用来进行残差缩放以及全局和局部残差学习。根据测试数据集结果,该网络在重建质量和运行速度上都达到了非常优异的性能。所提出的网络在性能、速度和硬件消耗方面均取得了良好的效果,具有较高的实用价值。