Joint Optimization for Multi-person Shape Models from Markerless 3D-Scans

Three-dimensional (3D) shape models have recently been used in various fields including machine designing, internet mall, and medical application. Therefore, efficient management and reuse of 3D shape models is becoming important with research on object searching of 3D shape models. 3D shape model searching requires taking into consideration rotation, scaling, and translation of models. This paper proposes a method to search 3D objects to include and account for the above conditions. The proposed method acquires 2D range images by rendering a 3D object from many viewpoints, and discretely approximating two of the three degrees of rotational freedom by a finite number of viewpoints. Using the phase correlation method on the range image one can estimate the rotation around one axis, include scaling and translation, and compare the similarities between the input with models in a dictionary. Experimental results show that whether models match or not match can be distinguished even when the supposed viewpoints are limited to a finite number.

Example-based statistical framework for parametric modeling of human body shapes

Ergonomic design of an EEG headset using 3D anthropometry

We investigate the problem of estimating the 3D shape of an object defined by a set of 3D landmarks, given their 2D correspondences in a single image. A successful approach to alleviating the reconstruction ambiguity is the 3D deformable shape model and a sparse representation is often used to capture complex shape variability. But the model inference is still challenging due to the nonconvexity in the joint optimization of shape and viewpoint. In contrast to prior work that relies on an alternating scheme whose solution depends on initialization, we propose a convex approach to addressing this challenge and develop an efficient algorithm to solve the proposed convex program. We further propose a robust model to handle gross errors in the 2D correspondences. We demonstrate the exact recovery property of the proposed method, the advantage compared to several nonconvex baselines and the applicability to recover 3D human poses and car models from single images.

Legg-Calvé-Perthes Disease (LCPD) often results in a permanent residual hip deformity, with long-term impacts on hip function. In the clinic, decisions on how to manage LCPD deformity are based on 2D radiographic measures such as the Stulberg grades. It is unclear whether these measures accurately represent complex, patient-specific 3D deformity, making it difficult to determine the best treatment approach. Statistical shape modeling (SSM) provides an objective and compact description of variability, but there is currently no 3D SSM that focuses solely on describing shape variability in LCPD. In this study, we have constructed an SSM of femurs with LCPD deformity, which will provide a foundation for future research into how deformity is measured in the clinic. Clinical magnetic resonance (MR) images (N=13 hips, 11 patients, 3 F/8 M) of affected hips were obtained in patients with stage IV LCPD (age range: 6–12 years, estimated Stulberg grades: II-V). MR volumes were resampled isotropically to the smallest voxel dimension (.47 – .63 mm), and two raters manually segmented the proximal femurs. ShapeWorks (SCI Institute, University of Utah, Salt Lake City, UT) was used to produce an SSM with 512 particles using an incremental optimization routine: corresponding particles were initially distributed and optimized on a subset of the five most similar femurs. The mean particle distribution of the initial model was then used to initialize the remaining eight shapes, followed by an additional optimization of the particle distribution. Differences in pose and scale between shapes were removed with generalized Procrustes analysis. Modes of shape variation were quantified using principal component analysis. The first four shape modes described 87.5% of the population variability, and qualitatively captured clinically relevant variables such as femoral head width and articular-trochanteric distance (see Figure 1). A significant association (p=0.04) was observed between shape mode 4 and asphericity of the femoral head (rho=0.58). A leave-one-out cross-validation of the model demonstrated good generalizability to unseen shapes, with a mean point-to-point reconstruction error of < 1 mm if > 4 modes were included. This SSM provides a continuous, accurate, and compact representation of 3D shape variation in LCPD. Limitations to this model include a small sample size, and thus the inability to control for age. In addition to expanding this model, future work will incorporate the acetabular side to describe joint congruence, and associate shape modes with radiographic parameters. For any figures or tables, please contact the authors directly.

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.

One of the fundamental problems of computer vision is to extract 3D shape and motion from images. This can be achieved when a scene or object is observed from different viewpoints or over a period of time. There is a wide range of applications, ranging from digitizing cultural heritage to vision-based autonomous robot navigation. This talk will present several approaches to solve this problem. First, we’ll discuss techniques for 3D shape recovery for static objects and scenes. One particular case is the 3D mapping and localization in large environments from images, e.g. urban 3D reconstruction from vehicleborne cameras or localization from cell-phone images. Next, we’ll shift our focus to modeling dynamic scenes, e.g. people who are moving around. In addition to explicitly 3D modeling an event, we'll consider the possibility to perform video-based rendering from casually captured videos. Speaker Bio-Sketch: Marc Pollefeys is a full professor in the Dept. of Computer Science of ETH Zurich since 2007 where he is the head of the Institute for Visual Computing and leads the Computer Vision and Geometry lab. He currently also remains associated with the Dept. of Computer Science of the University of North Carolina at Chapel Hill where he started as an assistant professor in 2002 and became an associate professor in 2005. Before this he was a postdoctoral researcher at the Katholieke Universiteit Leuven in Belgium, where he also received his M.S. and Ph.D. degrees in 1994 and 1999, respectively. His main area of research is computer vision. One of his main research goals is to develop flexible approaches to capture visual representations of real world objects, scenes and events. Dr. Pollefeys has received several prizes for his research, including a Marr prize, an NSF CAREER award, a Packard Fellowship and a European Research Council Starting Grant. He is the author or co-author of more than 130 peer-reviewed publications. He is the General Chair for the European Conference on Computer Vision 2014 (ECCV), was a Program Co-Chair for the IEEE Conference on Computer Vision and Pattern Recognition 2009 (CVPR), was general/program co-chair of the Third Symposium on 3D Data Processing, Visualization and Transmission and has organized workshops and courses at major vision and graphics conferences and has served on the program committees of many conferences. Prof. Pollefeys is/was on the Editorial Board of the IEEE Transactions on Pattern Analysis and Machine Intelligence and the International Journal of Computer Vision as well as several other journals in computer vision, graphics and robotics.

With the gradual increase in the demand for parametric human 3D models, the requirements for the accuracy of modeling and the quality of generation are getting higher and higher. In this paper, the human body structure model is constructed by 3D human posture estimation and spatio-temporal graph convolutional network, and after normalizing the data of the human body base, the 3D human body model based on the human body base is generated by combining the free deformation method, and the local light model is used to make the human body model more three-dimensional and real. In addition, the quality of 3D animation production is investigated by combining blind quality evaluation and validation analysis of the human body-based 3D model. The 3D human body modeling simulation error assessment has an error assessment root-means-square error that falls within 1.5%. In the validation analysis of model generation quality, the quality evaluation model proposed in this paper has a quality correlation coefficient and prediction accuracy of 0.9456 and 0.9454 on the dataset, respectively, and the performance of the ablation experiments and generalization experiments is stable. The mean value of the error between the animation production character generation effect and the actual testers is not more than 10mm.Combined with the research in this paper, it effectively improves the accuracy of human body modeling and provides an evaluation method for the quality of human 3D animation production and generation, which is of practical significance for its development.

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.

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.

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.

Realistic 3D human model reconstruction is an important component in computer graphics and computer vision. In particular, texturing on the surface of models is a key stage of reconstruction. In this paper, we dispose the texture mapping on the model’s surface as an optimization of image stitching, and present an effective method to generate a seamless, integrated and smooth texture on the surface of 3D human model. First, we build a corresponding Markov Random Field model with respect to color images and triangular meshes of the surface. On the basis of alpha-expansion optimization for this Markov Random Field model, a 2D translation coordinate of color image, as an adaptive iterative factor, is introduced into the optimization to match the color content at the boundary of adjacent meshes. That compensates for the misalignment of adjacent color images, which caused by the inaccuracy of depth data and multi-view misregistration. Then we apply Poisson blending to a composite vector field in gradient domain, to resolve the small but noticeable illumination variations between different color images. To repair the blank regions, we parameterize the model’s surface and project it onto a 2D plane. Then the K-Nearest Neighbor algorithm is applied to fill up the blank regions with texture contents. Finally, we evaluate our method by comparison with another three advanced methods on some human models, and the results demonstrate that our method of images stitching creates a best texture on the surface of 3D human model both in visual effect and quantitative analysis.

Human: An autocad based three dimensional anthropometric human model for workstation design

This paper proposes a semi-autonomous navigated master-slave system, for robot assisted remote echography for early trauma assessment. Two RGB-D sensors are used to capture real-time 3D information of the scene at the slave side where the patient is located. A 3D statistical shape model is built and used to generate a customized patient model based on the point cloud generated by the RGB-D sensors. The customized patient model can be updated and adaptively fitted to the patient. The model is also used to generate a trajectory to navigate a KUKA robotic arm and safely conduct the ultrasound examination. Extensive validation of the proposed system shows promising results in terms of accuracy and robustness.

The beam column connection is the most critical zone in a reinforced concrete frame. The strength of connection affects the overall behavior and performance of RC framed structures subjected to lateral load and axial loads. The study of critical parameters that affects the overall joint performances and response of the structure is important. Recent developments in computer technology have made possible the use of Finite element method for 3D modeling and analysis of reinforced concrete structures. Nonlinear finite element analysis of reinforced concrete interior beam column connection subjected to lateral loading was performed in order to investigate joint shear failure mode in terms of joint shear capacity, deformations and cracking pattern using ABAQUS software. A 3D solid shape model using 3D stress hexahedral element type (C3D8R) was implemented to simulate concrete behavior. Wire shape model with truss shape elements (T3D2) was used to simulate reinforcement’s behavior. The concrete and reinforcement bars were coupled using the embedded modeling technique. In order to define nonlinear behavior of concrete material, the concrete damage plasticity (CDP) was applied to the numerical model as a distributed plasticity over the whole geometry. The study was to investigate the most influential parameters affecting joint shear failure due to column axial load, beam longitudinal reinforcement ratio, joint panel geometry and concrete compressive strength. The Finite Element Model (FEM) was verified against experimental test of interior RC beam column connection subjected to lateral loading. The model showed good comparison with test results in terms of load-displacement relation, cracking pattern and joint shear failure modes. The FEA clarified that the main influential parameter for predicting joint shear failure was concrete compressive strength.