室内场景生成算法综述

室内场景生成任务是近年来热门的研究课题.它不仅能为计算机视觉任务提供天然带有标注的室内场景数据集,帮助其更好地理解场景,还能应用到诸多现实场景中,如机器人导航等.室内场景布局的多样性使得场景生成成为一项非常具有挑战性的任务.该文梳理了近年来在室内场景生成算法领域中的研究进展,从场景输入、场景上下文关系、场景表达方式、场...     

基于实例和约束的三维场景概念设计和系统实现

3D场景设计是VR建模中最重要也最耗人力的工作之一,如何解决该问题是一项重要的课题.本文提出一种新的基于实例和约束的三维场景概念设计方法.首先,根据所获取的场景实例中所蕴涵的不同层次的语义信息,对其进行场景元素过滤和场景语义标注,并由此构建三维场景实例库.相应地,对场景中可能出现的元素类别进行分类和语义标注,并建立场景元素库.接着,应用基于实例的方法,并结合场景设计过程中所涉及到的知识(约束),给出三维场景概念设计的一般方法;最后以一个实例对该方法做进一步的说明.研究表明,该方法符合人们对场景设计的一般过程.此外,由于场景实例和场景元素具有丰富的语义信息,使得所生成的场景除了常规的可视效果,还可以直接应用于虚拟现实环境以及三维动画等数字内容制作中.     

虚拟内窥镜实时体绘制技术研究

针对虚拟内窥镜技术中空体素较多和近景因素对视觉影响较大的特点，将一帧场景的绘制分为近景和远景两个部分．近景与远景的绘制分别采用加速的光线投射和改进的快速对象投影方法处理，较大地提高了当前帧的绘制速度；利用相邻帧的连贯性特点，将当前帧远景的绘制结果进行变换，得到下一帧远景的部分绘制结果，进一步提高了漫游的实时性。     

Scene appearance model based on spatial prediction

The appearance of a static scene as sensed by a camera changes considerably as a result of changes in the illumination that falls upon it. Scene appearance modeling is thus necessary for understanding which changes in the appearance of a scene are the result of illumination changes. For any camera, the appearance of the scene is a function of the illumination sources in the scene, the three-dimensional configuration of the objects in the scene and the reflectance properties of all the surfaces in the scene. A scene appearance model is described here as a function of the behavior of static illumination sources, within or beyond the scene, and arbitrary three-dimensional configurations of patches and their reflectance distributions. Based on the suggested model, a spatial prediction technique was developed to predict the appearance of the scene, given a few measurements within it. The scene appearance model and the prediction technique were developed analytically and tested empirically. Two potential applications are briefly explored.     

基于ACP方法的平行手机信令数据分析系统

随着交通拥堵和公共安全问题的日趋严重，传统方案在道路监测和区域监测方面不仅成本高，准确性和可靠性也无法保证，因此无法给用户提供一整套综合全面的出行路线规划及旅游目的地选择等方面的相关指导.本文提出基于ACP方法的平行手机信令数据分析系统，将解决上述问题.本文主要基于ACP方法，包括人工社会、计算实验和平行执行，构建基于手机信令的人工监控场景和实际监控场景.实际监控场景和人工监控场景平行执行，人工监控场景用来模拟和实验复杂的实际监控场景，通过大量计算实验，进行各种模型的训练与评估，通过平行执行不断地更新和优化，实时指导实际监控场景；同时实际监控场景将结果反馈给人工监控场景，对人工监控场景模型进行修正.通过实际监控场景和人工监控场景之间的不断优化，可有效提高手机信令系统的实时性、准确性和可靠性，并最终满足不断增长的实时用户需求，保证用户出行的舒适性及安全性.     

基于分层词袋模型的室外环境增量式场景发现

场景理解是机器人在多样化环境中自主执行任务的前提,而场景发现是场景理解的一个重要内容.由于具体场景在空间和时间上存在连续性,可以假定移动机器人在某一段时间内处于同一场景,并且属于同一场景的图像序列的视觉观感是相似的,因此提出无需先验知识的增量式室外场景发现,通过分层词袋模型建立图像和场景的联系,使得场景发现过程更加类似人类认知模式.对于机器人实时获取的每一副图像,首先将其分块,然后利用动态聚类算法增量式地得到相应的低层词典,并据此词典提取高层词袋模型特征,接下来,再用另一动态聚类算法增量式地完成场景发现,从而判断当前图像属于一个已经历场景,或未经历场景,直到发现新场景.实验结果证明,该方法能够在没有先验知识的情况下有效完成自主场景发现.     

图神经网络下的生成式室内家具摆放

自动的室内家具摆放在家居设计、动态场景生成等应用中具有显著的意义.传统算法往往通过显式的空间、语义和功能性上物体之间的关系来理解场景的内部结构,并进一步辅助室内场景的生成.随着大规模室内场景数据集的出现,提出将零散的输入家具编码进图结构,并利用图神经网络中迭代的消息传递隐式地学习场景的分布先验.为了满足家具摆放的多样性...     

基于场景图的实时交互视景系统平台设计

三维场景组织管理中经常采用的空间数据结构--场景图的具体实现,包括场景数据的组织管理,可见性剔除、节点遍历、优化处理、碰撞检测等.在基于场景图的基础上设计并实现了一个实时交互式视景系统开发平台,给出了系统的结构框图、工作流程与信息交互关系,并对视景系统平台的视点控制、场景参数的应用定义文件输出以及场景图像捕捉和视频输出功能进行了详细介绍.平台同时提供了一套基于场景图的可供二次开发的三维图形应用程序接口.     

视觉场景描述及其效果评价

作为计算机视觉、多媒体、人工智能和自然语言处理等领域的交叉性研究课题,视觉场景描述的研究内容是自动生成一个或多个语句用于描述图像或视频中呈现的视觉场景信息.视觉场景中内容的丰富性和自然语言表达的多样性使得视觉场景描述成为一项充满挑战的任务,综述了现有视觉场景描述方法及其效果评价.首先,论述了视觉场景描述的定义、研究任务及方法分类,简要分析了视觉场景描述与多模态检索、跨模态学习、场景分类、视觉关系检测等相关技术的关系;然后分类讨论视觉场景描述的主要方法、模型及研究进展,归纳日渐增多的基准数据集;接下来,梳理客观评价视觉场景描述效果的主要指标和视觉场景描述技术面临的问题与挑战,最后讨论未来的应用前景.     

基于Java3D化工网络虚拟场景的构建

分析3D技术的异同,选取Java3D构建化工网络虚拟场景。以超临界萃取的实验场景为研究对象,以场景的构建技术为区分标准,分别描述了构建静态场景和动态场景的实现技术。静态场景包括单元设备和复杂流程的构建;动态场景包括表面贴图和动态组合的构建,动态组合又细分为Moved object、Animated object、Picked object三类内容分支。静态场景与动态场景混合构建的方式展示了实验操作和实验现象。最后对该领域的前景作出展望并提出未来的研究方向。     

Automatic 3D Indoor Scene Updating with RGBD Cameras

Since indoor scenes are frequently changed in daily life, such as re‐layout of furniture, the 3D reconstructions for them should be flexible and easy to update. We present an automatic 3D scene update algorithm to indoor scenes by capturing scene variation with RGBD cameras. We assume an initial scene has been reconstructed in advance in manual or other semi‐automatic way before the change, and automatically update the reconstruction according to the newly captured RGBD images of the real scene update. It starts with an automatic segmentation process without manual interaction, which benefits from accurate labeling training from the initial 3D scene. After the segmentation, objects captured by RGBD camera are extracted to form a local updated scene. We formulate an optimization problem to compare to the initial scene to locate moved objects. The moved objects are then integrated with static objects in the initial scene to generate a new 3D scene. We demonstrate the efficiency and robustness of our approach by updating the 3D scene of several real‐world scenes.     

多风格融合的复杂森林场景自适应可视化

为了保证森林场景可视化时的真实感,同时保持动态森林场景生成时间的恒定性,本文提出了一种多风格融合的复杂森林场景自适应可视化方法。该方法利用基于视距的模型分布函数来控制树木模型的分布比例,从而建立多风格融合的森林可视化模型;在此基础上,根据复杂森林场景中树木生长模型的计算时间、三维树木绘制时间的估算结果,以及树木的视觉重要性,确定生成森林场景的最佳方案。该方法能够使复杂动态森林场景的生成时间保持较好的稳定性,并且在可视化过程中根据仿真效果动态调整绘制策略。为了验证该方法的有效性和实用性,在动态生长的森林仿真场景中对本文的方法进行了实验和应用。应用结果表明,多风格融合的森林场景自适应可视化方法能在保证森林场景可视化真实感的基础上,有效地提升复杂森林场景的绘制速度,使森林场景的快速漫游具有更好的稳定性和流畅性。     

Three-dimensional scene flow

Just as optical flow is the two-dimensional motion of points in an image, scene flow is the three-dimensional motion of points in the world. The fundamental difficulty with optical flow is that only the normal flow can be computed directly from the image measurements, without some form of smoothing or regularization. In this paper, we begin by showing that the same fundamental limitation applies to scene flow; however, many cameras are used to image the scene. There are then two choices when computing scene flow: 1) perform the regularization in the images or 2) perform the regularization on the surface of the object in the scene. In this paper, we choose to compute scene flow using regularization in the images. We describe three algorithms, the first two for computing scene flow from optical flows and the third for constraining scene structure from the inconsistencies in multiple optical flows.     

基于Applet的场景管理系统的设计

当场景本身还包含多个运动物体时,所有的游戏实体(包括场景角色)、绘制和更新过程仍在一个applet中进行,场景角色的冲突检测和绘制会使处理器变慢.让applet只处理游戏的初始化并驱动主事件循环,这时就需要场景管理系统来控制场景的处理任务.     

Video scene analysis in 3D wavelet transform domain

This paper proposes a novel scene analysis algorithm based on three-dimensional discrete wavelet transform (3D DWT). Based on the correlation among the adjacent frames, video frames can be considered as four categories: abrupt scene transition, motion scene, gradual scene transition and static scene, which are ranked from low to high according to the strength of the correlation. Through the investigation of the particular temporal and spatial distribution of each category, the correlation among adjacent frames could be described by the 3D DWT coefficients related statistical features, which are the energy of high-frequency coefficients difference, the sum of high-frequency coefficients magnitudes and the difference of low-frequency coefficients magnitudes. The energy of high-frequency coefficients difference is first used to detect the abrupt scene transition including cut and flashlight. Then all the three features are input to SVM for the purpose of analyzing the residual scenes and detecting the gradual scene transition, such as dissolve and fade. Experimental results show the method to be effective not only for the abrupt scene transition detection, but also for the gradual scene transition detection.     

基于深度学习的场景识别方法综述

随着深度学习的快速发展,基于深度学习的场景识别方法逐渐取代传统的基于手工特征的场景识别方法,成为未来研究的主要方向。针对基于深度学习的场景识别方法,对基本思想进行了总结,将其大体分为以下四类：深度学习与视觉词袋结合场景识别法、基于显著部分的场景识别法、多层特征融合场景识别法、融合知识表示的场景识别法,分析了各个方法的特点及局限性,并对识别效果进行了比较,最后对未来研究方向进行展望。     

基于虚拟现实技术的飞行视景仿真

飞行视景仿真是飞行仿真的一个重要组成部分，它的视觉效果和逼真程度将直接影响整个飞行模拟器的逼真度。讨论了飞行视景系统的构成、视景的生成与显示，并介绍了几种开发视景系统的工具软件，重点讨论了虚拟现实技术在飞行视景仿真中的应用和关键技术。     

SUN Database: Exploring a Large Collection of Scene Categories

Progress in scene understanding requires reasoning about the rich and diverse visual environments that make up our daily experience. To this end, we propose the Scene Understanding database, a nearly exhaustive collection of scenes categorized at the same level of specificity as human discourse. The database contains 908 distinct scene categories and 131,072 images. Given this data with both scene and object labels available, we perform in-depth analysis of co-occurrence statistics and the contextual relationship. To better understand this large scale taxonomy of scene categories, we perform two human experiments: we quantify human scene recognition accuracy, and we measure how typical each image is of its assigned scene category. Next, we perform computational experiments: scene recognition with global image features, indoor versus outdoor classification, and “scene detection,” in which we relax the assumption that one image depicts only one scene category. Finally, we relate human experiments to machine performance and explore the relationship between human and machine recognition errors and the relationship between image “typicality” and machine recognition accuracy.     

The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding

In this paper we present the first large-scale scene attribute database. First, we perform crowdsourced human studies to find a taxonomy of 102 discriminative attributes. We discover attributes related to materials, surface properties, lighting, affordances, and spatial layout. Next, we build the “SUN attribute database” on top of the diverse SUN categorical database. We use crowdsourcing to annotate attributes for 14,340 images from 707 scene categories. We perform numerous experiments to study the interplay between scene attributes and scene categories. We train and evaluate attribute classifiers and then study the feasibility of attributes as an intermediate scene representation for scene classification, zero shot learning, automatic image captioning, semantic image search, and parsing natural images. We show that when used as features for these tasks, low dimensional scene attributes can compete with or improve on the state of the art performance. The experiments suggest that scene attributes are an effective low-dimensional feature for capturing high-level context and semantics in scenes.     

基于古典园林借景理法的情景化产品设计研究

随着高科技的迅猛发展,人们的生活方式更加多样化,工业产品的设计越来越注重情景意义。在分析情景化设计理念和古典园林借景理法基础上,进行了生活情景研究、情景化设计定位和情景符号化的分析,提出了产品设计的情景化设计方法,把产品设计提升到生活方式设计和人文设计的层次,拓展产品的内涵与外延,使产品能够触物生情、传情达意。从而使工业产品更加"自然化"、"人性化",提高人们的生活质量。