3-D shape model retrieval using multi range image phase correlation method

We propose a markerless end-to-end training framework for parametric 3D human shape models. The training of statistical 3D human shape models with minimal supervision is an important problem in computer vision. Contrary to prior work, the whole training process (i) uses a differentiable shape model surface and (ii) is trained end-to-end by jointly optimizing all parameters of a single, self-contained objective that can be solved with slightly modified off-the-shelf non-linear least squares solvers. The training process only requires a compact model definition and an off-the-shelf 2D RGB pose estimator. No pre-trained shape models are required. For training (iii) a medium-sized dataset of approximately 1000 low-resolution human body scans is sufficient to achieve competitive performance on the challenging FAUST surface correspondence benchmark. The training and evaluation code will be made available for research purposes to facilitate end-to-end shape model training on novel datasets with minimal setup cost.

I propose novel 3D shape analysis and modeling algorithm for active contours using variational scheme. The proposed algorithm utilizes an unknown surface of 3D shape by normal to 3D shape analysis and modeling. It would be used to get high quality reconstruction's results from many dimensions' data. I give it by utilizing continuous anisotropism weights would finish comparable ameliorate to surface reconstruction.

This paper considers the segmentation of range image measurements into surface patches which are either plane or curved and which are described formally by a function. After a formal description of the segmentation, we present and compare three methods suited for plane and curved patch segmentation and show the results of experiments conducted for testing their practical behaviour. The two first methods use the classical approach of region growing whereas the third method is based on a relaxation process. This original and last method exhibits simplicity and low computational complexity. Thanks to its parallel nature, it can be considered as a good candidate for range image segmentation in real-time applications.

This study was conducted to determine the margins and timing of replanning by assessing the daily interfractional cervical and uterine motions using magnetic resonance (MR) images. Eleven patients with cervical cancer, who underwent intensity-modulated radiotherapy (IMRT) in 23-25 fractions, were considered in this study. The daily and reference MR images were converted into three-dimensional (3D) shape models. Patient-specific anisotropic margins were calculated from the proximal 95% of vertices located outside the surface of the reference model. Population-based margins were defined as the 90th percentile values of the patient-specific margins. The expanded volume of interest (expVOI) for the cervix and uterus was generated by expanding the reference model based on the population-based margin to calculate the coverage for daily deformable mesh models. For comparison, expVOIconv was generated using conventional margins: right (R), left (L), anterior (A), posterior (P), superior (S), and inferior (I) were (5, 5, 15, 15, 10, 10) and (10, 10, 20, 20, 15, 15) mm for the cervix and uterus, respectively. Subsequently, a replanning scenario was developed based on the cervical volume change. ExpVOIini and expVOIreplan were generated before and after replanning, respectively. Population-based margins were (R, L, A, P, S, I) of (7, 7, 11, 6, 11, 8) and (14, 13, 27, 19, 15, 21) mm for the cervix and uterus, respectively. The timing of replanning was found to be the 16th fraction, and the volume of expVOIreplan decreased by >30% compared to that of expVOIini . However, margins cannot be reduced to ensure equivalent coverage after replanning. We determined the margins and timing of replanning through detailed daily analysis. The margins of the cervix were smaller than conventional margins in some directions, while the margins of the uterus were larger in almost all directions. A margin equivalent to that at the initial planning was required for replanning.

Need to organize 3D shape data has prompted studies on comparison and retrieval of 3D shape models. Being able to query 3D shape models by words, in addition to 3D model examples and 2D sketches, would be quite beneficial. This paper proposes a method to associate whole 3D models (e.g., automobile) as well as their parts (e.g., tire, body, engine) with word labels so that the 3D model can be queried by words. The associations between 3D shapes and words are learned from a dataset of 3D models whose whole model and segmented parts are labeled with words. Feature vectors of these words (distributed representation) and feature vectors of whole and partial geometries of 3D models are embedded, by Word Shape embedding Network (WSN) into a common feature embedding space. As the word feature vectors are learned by Word2Vec trained on Wikipedia corpus, the common embedding space can be queried by a wide variety of words that are not included in the labeled 3D model dataset. Experimental evaluation has shown that, with the proposed algorithm, 3D shape can be queried by labels of either whole or part shape, or labels that are semantically close but not included in the original 3D model dataset.

A technique to generate a photorealistic three-dimensional (3D) image and color-textured model using a dedicated optical digitizer is presented. The proposed technique is started with the range and texture image acquisition from different viewpoints, followed by the registration and integration of multiple range images to get a complete and nonredundant point cloud that represents a real-life object. The accuracy of the range image and the precision of correspondence between the range image and texture image are guaranteed by sensor system calibration. Based on the point cloud, a geometric model is established by considering the connectivity of adjacent range image points. In order to enhance the photorealistic effect, we suggest a texture blending technique that utilizes a composite-weight strategy to blend the texture images within the overlapped region. This technique allows more efficient removal of the artifacts existing in the registered texture image, leading to a 3D image with photorealistic quality and color-texture modeling. Experimental results are also presented to testify to the validity of the proposed method.

Context. Detailed knowledge of shapes is necessary for modeling certain processes affecting small Solar System bodies, such as the influence of radiative effects – like the YORP effect – on rotation. For meteoroids and small monolithic asteroids, such shapes have not been available up till now. This has strongly limited the possibilities of theoretical studies of the non-gravitational phenomena acting on these bodies. Aims. Our goal is to create a database of digital 3D shape models that would be suitable for describing the shapes of meteoroids and small monolithic asteroids. Methods. We performed catastrophic disruption experiments on samples from L3-6 ordinary chondrite NWA 869 and terrestrial tephriphonolite, including one hypervelocity impact and two explosion experiments. We selected fragments with masses of m ≥ 0.2 g that originated from the interior of the samples and did not contain the original target surface. Their size range is approximately 5–24 mm. Their shapes were digitized using X-ray computed tomography, with voxel sizes of about 50 µm. Results. The resulting database contains 868 shape models in Wavefront OBJ format, as well as a list of the basic properties of each one. The numbers of triangular surface facets of these models range from ∼20 000 to ∼760 000. These shape models correspond to meteoroids and small asteroids created by hypervelocity collisions. When using this database for a particular purpose, it is necessary to consider the selection of appropriate models based on the absence or presence of certain morphological features, such as chondrules, significant cracks, or minor artefacts. The possible presence of these features in a specific shape model has been recorded in the database.

Multi-view range image registration is a significant and challenging problem for 3D modeling. This paper presents a reference shape based multi-view range image registration algorithm. First, a set of Rotational Projection Statistics (RoPS) features are extracted from the input range images. Next, the reference shape is initialized by selecting a range image from the input. The reference shape is then iteratively updated by registering itself with the remaining range images. The registration between the reference shape and any range image is completed by RoPS feature matching. Finally, all input range images are registered according to their corresponding reference shapes. A number of experiments were performed to test the performance of our algorithm. The experimental results show that the reference shape based algorithm can perform multi-view registration on a mixed set of unordered range images corresponding to several different objects. It is also very accurate and efficient. It outperformed the state-of-the-arts including the spanning tree based and connected graph based algorithms.

Patellofemoral pain (PFP) is suggested as a precursor of patellofemoral osteoarthritis (PFOA) later in life. This hypothesis is based on shared risk factors for both diseases, such as deviating alignment parameters. In patients with PFOA, certain 2D alignment parameters and 3D shape variations are associated with the progression of PFOA. The relationship among alignment, shape, and PFP persistence remains unclear to date. To investigate the association between 2D alignment parameters, 3D bone shape variations, and PFP persistence. Questionnaire and magnetic resonance imaging (MRI) data from 64 patients between 14 and 40 years of age with PFP were selected from a case-control study. Participants who completed follow-up questionnaires at one or two years of follow-up were included. PFP persistence, measured using a 7-point Likert scale, was dichotomized. Structural abnormalities were scored using the MRI Osteoarthritis Knee Score (MOAKS), and alignment parameters were determined following standardized methods. The patellae were segmented from the MRI using a semi-automatic segmentation algorithm, and a 3D statistical shape model was created. Shape modes explaining at least 1% of total population variation were included. Regression analyses were performed to determine the association among baseline function (anterior knee pain scale (AKPS)), MOAKS features, alignment parameters, 3D patellar shape modes, and PFP persistence. Fifty-five participants completed follow-up questionnaires and were included in the current analyses. Participants had a mean (standard deviation) age of 23.2 (6.8), and 58.2% were female. AKPS increased statistically significantly from 65.7 (10.6) at baseline to 75.9 (14.9) at follow-up. Nineteen patellar shape modes were included in the analyses, of which four showed a P-value <0.05; however, they were not statistically significant after applying Bonferroni correction. No associations were found among MOAKS, alignment parameters, shape modes, and PFP persistence in the adjusted models. Only AKPS at baseline was associated with pain severity at follow-up (β​=​-0.13, 95% confidence interval: -0.20; -0.07). No statistically significant associations were found among structural abnormalities, 2D alignment, or 3D shape modes, and PFP persistence. Only worse AKPS at baseline was associated with persistent PFP, suggesting that baseline function might be a better predictor than structural abnormalities, alignment, or bone shape. III.

3D shape modeling using a self-developed hand-held 3D laser scanner and an efficient HT-ICP point cloud registration algorithm

3D shape models are naturally parameterized using vertices and faces, i.e., composed of polygons forming a surface. However, current 3D learning paradigms for predictive and generative tasks using convolutional neural networks focus on a voxelized representation of the object. Lifting convolution operators from the traditional 2D to 3D results in high computational overhead with little additional benefit as most of the geometry information is contained on the surface boundary. Here we study the problem of directly generating the 3D shape surface of rigid and non-rigid shapes using deep convolutional neural networks. We develop a procedure to create consistent &#x2018;geometry images&#x2019; representing the shape surface of a category of 3D objects. We then use this consistent representation for category-specific shape surface generation from a parametric representation or an image by developing novel extensions of deep residual networks for the task of geometry image generation. Our experiments indicate that our network learns a meaningful representation of shape surfaces allowing it to interpolate between shape orientations and poses, invent new shape surfaces and reconstruct 3D shape surfaces from previously unseen images. Our code is available at https://github.com/sinhayan/surfnet.

Classical machine vision is difficult to be used as practical 3D vision because it loses depth when projecting 3D objects into 2D images and then has ambiguity when reconstructing 3D object. In contrast, range images, i.e. 3D images, keep the invariance properties of 3D objects, which makes the image processing tasks easier. This paper develops the prototype of spatial encoder using laser scanning method. Range images are obtained based on encoded images produced by our encoder.

This paper presents a novel method for face alignment under unknown head poses and nonrigid warp, within the framework of markov random field. The proposed method learns a 3D face shape model comprised of 31 facial features and a texture model for each facial feature from a 3D face database. The models are combined to serve as the unary, pairwise and high order constraints of the markov random field. The facial features are located by minimizing the potential function of markov random field, which is solved with dual decomposition. The main contribution of this paper is composed of three aspects. First, Random Project Tree is utilized to learn the manifold structure of the facial feature appearance under different view points. Second, a 3D face shape model is learned to capture the linear part of face shape distribution due to the change of identity and expression, which is served as the high order constraints. Third, Markov random field is introduced to model the nonlinear part of the face shape distribution, and also to deal with occlusion of facial features due to head pose variation or ornaments. Experiments was taken on the Texas 3D face database and face images downloaded from the Internet, results shows capability of adapting large head pose variations of the method.KeywordsFace ImageFacial FeatureMarkov Random FieldFace ShapeTexture ModelThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

It is not only interesting to predict how an individual of a relatively young age will look in the future but also to reconstruct the facial appearance in the past during childhood. It can be even more desirable when different circumstances, behavior and lifestyle and their impacts on the facial shape appearance as a consequence are taken into account. Such may be applicable for many practical reasons in healthcare, forensics psychology, missing people and children, etc. This paper presents the 3D Face Time Machine Matrix (FT2M), a 3D Dynamic Shape Model which is a fusion of two models of ageing and rejuvenation with facial shape variations due to lifestyle and behavioral factors. This dynamic model is learned from a database of three dimensional facial images which is built by ten individual age groups between 3 to 75 years old. 3D facial aging modeling is a complex process since it affects both the shape and texture of the face. We propose a Dynamic face model to transform the given input face to his youthful or adulthood appearance by taking into account his lifestyle and behavioral traits and the probable changes may occur in perceptible appearance by altering its shape and texture simultaneously.

An adaptive range image coding algorithm for the geometry compression of large-scale 3D point clouds (LS3DPCs) is proposed in this work. A terrestrial laser scanner generates an LS3DPC by measuring the radial distances of objects in a real world scene, which can be mapped into a range image. In general, the range image exhibits different characteristics from an ordinary luminance or color image, and thus the conventional image coding techniques are not suitable for the range image coding. We propose a hybrid range image coding algorithm, which predicts the radial distance of each pixel using previously encoded neighbors adaptively in one of three coordinate domains: range image domain, height image domain, and 3D domain. We first partition an input range image into blocks of various sizes. For each block, we apply multiple prediction modes in the three domains and compute their rate-distortion costs. Then, we perform the prediction of all pixels using the optimal mode and encode the resulting prediction residuals. Experimental results show that the proposed algorithm provides significantly better compression performance on various range images than the conventional image or video coding techniques