Pose normalization of 3D models via reflective symmetry on panoramic views

A novel pose normalization method, based on reflective symmetry computed on panoramic views, is presented. Qualitative and experimental investigation in 3D data-sets has led us to the observation that most objects possess a single plane of symmetry. Our approach is thus guided by this observation. Initially, through an iterative procedure, the symmetry plane of a 3D model is estimated, thus computing the first axis of the model. This is achieved by rotating the 3D model and computing reflective symmetry scores on panoramic view images. The other principal axes of the 3D model are estimated by computing the variance of the 3D model’s panoramic views. The proposed method is incorporated in a hybrid scheme, that serves as the pose normalization method in a state-of-the-art 3D object retrieval system. The effectiveness of this system, using the hybrid pose normalization scheme, is evaluated in terms of retrieval accuracy and the results clearly show improved performance against current approaches.     

融合信息熵和CNN 的基于手绘的三维模型检索

基于手绘草图的三维模型检索(SBSR)已成为三维模型检索、模式识别与计算机视 觉领域的一个研究热点。与传统方法相比,基于卷积神经网络(CNN)的三维深度表示方法在三 维模型检索任务中性能优势非常明显。本文提出了一种基于手绘图像融合信息熵和CNN 的三 维模型检索方法。首先,通过计算模型投影图的信息熵得到模型的代表性视图,并将代表性视 图经过边缘检测等处理得到三维模型投影图的轮廓图像;然后,将轮廓图像和手绘草图输入到 CNN 中提取特征描述子,并进行特征匹配。本文方法在Shape Retrieval Contest (SHREC) 2012 数据库和SHREC 2013 数据库上进行实验。实验证明,该方法的效果较其他传统方法检索准确 度更高。     

离散ADMM方法下像素与对象基元协同优化的遥感影像无监督语义分割

语义分割是遥感影像分析中的重要技术之一。现有的方法（如基于深度卷积神经网络的方法等）虽然在语义分割中取得了显著进展,但往往需要大量训练数据。基于图模型的马尔可夫随机场模型（Markov random field model,MRF）提出了一种不依赖训练数据的无监督语义分割思路,可以有效地刻画地物空间关系,并对地物空间分布的统计规律进行建模。但现有的MRF模型方法通常建立在基于像素或对象的单一粒度基元上,难以充分利用影像信息,语义分割效果不佳。针对上述问题,引入交替方向乘子法 （alternative direction method of multiplier,ADMM）并将其离散化,提出了一种像素与对象基元协同的MRF模型无监督语义分割方法（MRF-ADMM）。首先构建像素基元和对象基元两个概率图,其中像素基元概率图用于刻画影像的细节信息,保持语义分割的边界;对象基元概率图用于描述较大范围的空间关系,以应对遥感影像地物内部的高异质性,使分割结果中地物内部具有良好的区域完整性。在模型求解过程中,针对像素和对象基元的特点,提出了一种离散化的ADMM方法,并将其用于两种基元类别标记的传递与更新,实现像素基元细节信息和对象基元区域信息的协同优化。高分二号和航拍影像等不同数据库不同类型遥感影像的语义分割实验结果表明,相较于现有的MRF模型,提出的MRF-ADMM方法能有效地协同不同粒度基元的优点,优化语义分割结果。     

基于球体投影的三维模型检索

针对草图检索三维模型时存在的域不匹配和如何选取视图等问题,提出一种基于球体投影的三维模型检索方法。针对域不匹配问题,提出基于球体投影的二维视图获取方法,并使用高斯差分和贝塞尔曲线完成线图的提取;利用草图和投影图像之间的关系构建分类器,以获取模型的最优视图;通过两个Siamese网络获取草图和二维视图的特征,并用联合贝叶斯（Joint Bayesian）方法来融合二者的输出,从而获得最终结果。实验证明了该方法的可行性,与其他方法相比具有更好的检索效果。     

Multi-scale energy optimization for object proposal generation

In this paper, we present an object proposal generation method by applying energy optimization into superpixel merging algorithms in a multiscale framework, which could generate possible object locations in one image. As images in object detection datasets always enjoy high diversity, we adopt two different energy functions with multi-scales. Thus, our method enjoys the strength of global search, which is strong in locating salient object by concerning the whole image at one merge iteration, as well as the strength of local search which is more likely to recall the un-salient instances. What’s more, unlike most superpixel merging algorithms that are based on diversified segmentation results, our approach takes advantage of robust edge detection and segments each image only once, which greatly reduces the number of proposals. Experiments on PASCAL VOC 2007 test set show that the proposed method outperforms most previous superpixel merging based methods and also could compete with state-of-the-art proposal generators.     

协同目标性指导下的多图像联合分割算法

提出一种协同分割算法,使包含同类目标的多幅图像相互作用,从而将目标从各自图像的背景中分离出来。首先,分别从单幅图像自身角度和多幅同类目标图像相互作用的角度出发,计算出图像中每个像素或区域属于前景或背景的似然概率,从而得到协同目标性映射图。这个映射图描述了目标的位置和几何形状信息,然后阈值化这个映射图作为图像分割真值来训练一个关于超像素的二值分类器,用训练好的分类器预测出每个超像素的前背景似然概率作为外观先验信息,与几何先验信息一并送入条件随机场模型,从而实现对图像目标的分割。在MSRC和iCoseg两个数据库上的测试结果表明该算法的分割效果优于同类方法。     

Two-stage deep learning for supervised cross-modal retrieval

This paper deals with the problem of modeling internet images and associated texts for cross-modal retrieval such as text-to-image retrieval and image-to-text retrieval. Recently, supervised cross-modal retrieval has attracted increasing attention. Inspired by a typical two-stage method, i.e., semantic correlation matching(SCM), we propose a novel two-stage deep learning method for supervised cross-modal retrieval. Limited by the fact that traditional canonical correlation analysis (CCA) is a 2-view method, the supervised semantic information is only considered in the second stage of SCM. To maximize the value of semantics, we expand CCA from 2-view to 3-view and conduct supervised learning in both stages. In the first learning stage, we embed 3-view CCA into a deep architecture to learn non-linear correlation between image, text and semantics. To overcome over-fitting, we add the reconstruct loss of each view into the loss function, which includes the correlation loss of every two views and regularization of parameters. In the second stage, we build a novel fully-convolutional network (FCN), which is trained by joint supervision of contrastive loss and center loss to learn better features. The proposed method is evaluated on two publicly available data sets, and the experimental results show that our method is competitive with state-of-the-art methods.

     

3D object retrieval via range image queries in a bag-of-visual-words context

3D object retrieval based on range image queries that represent partial views of real 3D objects is presented. The complete 3D models of the database are described by a set of panoramic views, and a Bag-of-Visual-Words model is built using SIFT features extracted from them. To address the problem of partial matching, we suggest a histogram computation scheme, on the panoramic views, that represents local information by taking into account spatial context. Furthermore, a number of optimization techniques are applied throughout the process for enhancing the retrieval performance. Its superior performance is shown by evaluating it against state-of-the-art methods on standard datasets.     

Automatic 3D object segmentation in multiple views using volumetric graph-cuts

We propose an algorithm for automatically obtaining a segmentation of a rigid object in a sequence of images that are calibrated for camera pose and intrinsic parameters. Until recently, the best segmentation results have been obtained by interactive methods that require manual labelling of image regions. Our method requires no user input but instead relies on the camera fixating on the object of interest during the sequence. We begin by learning a model of the object’s colour, from the image pixels around the fixation points. We then extract image edges and combine these with the object colour information in a volumetric binary MRF model. The globally optimal segmentation of 3D space is obtained by a graph-cut optimisation. From this segmentation an improved colour model is extracted and the whole process is iterated until convergence.     

Segmentation for remote-sensing imagery using the object-based Gaussian-Markov random field model with region coefficients

The Markov random field (MRF) model is a widely used method for remote-sensing image segmentation, especially the object-based MRF (OMRF) method has attracted great attention in recent years. However, the OMRF method usually fails to capture the correlation between regional features by just considering the mixed-Gaussian model. In order to solve this problem and improve the segmentation accuracy, this article proposes a new method, object-based Gaussian-Markov random field model with region coefficients (OGMRF-RC), for remote-sensing image segmentation. First, to describe the complicated interactions among regional features, the OGMRF-RC method employs the region size and edge information as region coefficients to build the object-based linear regression equation (OLRE) for each region. Second, the classic Gaussian-Markov model is extended to region level for modelling the errors in OLREs. Finally, the segmentation is achieved through a principled probabilistic inference designed for the OGMRF-RC method. Experimental results over synthetic texture images and remote-sensing images from different datasets show that the proposed OGMRF-RC method can achieve more accurate segmentation than other state-of-the-art MRF-based methods and the method using convolutional neural networks.     

基于多分辨率马尔可夫随机场运动目标分割

提出一种基于三维时空小波变换和马尔可夫随机场(MarkovRandomField)模型的多分辨率运动目标分割算法。该算法利用三维时空小波变换对图像序列进行分解得到多分辨率的图像序列,并在此基础上建立多分辨率的马尔可夫随机场模型,构造相应的能量函数。通过条件迭代模型优化算法(IteratedConditionalModes)求解能量函数的最优解,得出标记场,提取出运动目标。实验结果证明,该算法能够很好地消除了单一分辨率的MRF运动检测结果中"空洞"现象,对运动目标分割具有很好的分割效果。     

In the wild image retrieval and clustering for 3D cultural heritage landmarks reconstruction

One of the main characteristics of Internet era is the free and online availability of extremely large collections of images located on distributed and heterogeneous platforms over the web. The proliferation of millions of shared photographs spurred the emergence of new image retrieval techniques based not only on images’ visual information, but on geo-location tags and camera exif data. These huge visual collections provide a unique opportunity for cultural heritage documentation and 3D reconstruction. The main difficulty, however, is that the internet image datasets are unstructured containing many outliers. For this reason, in this paper a new content-based image filtering is proposed to discard image outliers that either confuse or significantly delay the followed e-documentation tools, such as 3D reconstruction of a cultural heritage object. The presented approach exploits and fuses two unsupervised clustering techniques: DBSCAN and spectral clustering. DBSCAN algorithm is used to remove outliers from the initially retrieved dataset and spectral clustering discriminate the noise free image dataset into different categories each representing characteristic geometric views of cultural heritage objects. To discard the image outliers, we consider images as points onto a multi-dimensional manifold and the multi-dimensional scaling algorithm is adopted to relate the space of the image distances with the space of Gram matrices through which we are able to compute the image coordinates. Finally, structure from motion is utilized for 3D reconstruction of cultural heritage landmarks. Evaluation on a dataset of about 31,000 cultural heritage images being retrieved from internet collections with many outliers indicate the robustness and cost effectiveness of the proposed method towards a reliable and just-in-time 3D reconstruction than existing state-of-the-art techniques.     

Adaptive pixon represented segmentation (APRS) for 3D MR brain images based on mean shift and Markov random fields

In this paper, we proposed an adaptive pixon represented segmentation (APRS) algorithm for 3D magnetic resonance (MR) brain images. Different from traditional method, an adaptive mean shift algorithm was adopted to adaptively smooth the query image and create a pixon-based image representation. Then K-means algorithm was employed to provide an initial segmentation by classifying the pixons in image into a predefined number of tissue classes. By using this segmentation as initialization, expectation-maximization (EM) iterations composed of bias correction, a priori digital brain atlas information, and Markov random field (MRF) segmentation were processed. Pixons were assigned with final labels when the algorithm converges. The adoption of bias correction and brain atlas made the current method more suitable for brain image segmentation than the previous pixon based segmentation algorithm. The proposed method was validated on both simulated normal brain images from BrainWeb and real brain images from the IBSR public dataset. Compared with some other popular MRI segmentation methods, the proposed method exhibited a higher degree of accuracy in segmenting both simulated and real 3D MRI brain data. The experimental results were numerically assessed using Dice and Tanimoto coefficients.     

Segmentation of fuzzy images: a novel and fast two-step pseudo MAP method

This paper presents a new two-step pseudo maximum a posteriori (MAP) segmentation method for the Markov random field (MRF)-modeled image because the exact MAP estimation is hard to implement due to intractable complexity. The expectation maximization (EM) and Markov Chain Monte Carlo (MCMC) methods are adopted to estimate the parameters for the MRF model due to their comparatively good performance. Although the image segmentation algorithms via graph cuts have become very popular nowadays, our proposed algorithm still performs significantly better in automatic identification and segmentation of fuzzy images than them, which is shown by the quantitative results on synthesized images. In practical applications, the proposed two-step pseudo MAP method is superior in segmenting the fuzzy laser images reflected from the weld pool surfaces during the P-GMAW welding process.