RESUMEN

Accurate and robust 3D human modeling from a single image presents significant challenges. Existing methods have shown potential, but they often fail to generate reconstructions that match the level of detail in the input image. These methods particularly struggle with loose clothing. They typically employ parameterized human models to constrain the reconstruction process, ensuring the results do not deviate too far from the model and produce anomalies. However, this also limits the recovery of loose clothing. To address this issue, we propose an end-to-end method called IHRPN for reconstructing clothed humans from a single 2D human image. This method includes a feature extraction module for semantic extraction of image features. We propose an image semantic feature extraction aimed at achieving pixel model space consistency and enhancing the robustness of loose clothing. We extract features from the input image to infer and recover the SMPL-X mesh, and then combine it with a normal map to guide the implicit function to reconstruct the complete clothed human. Unlike traditional methods, we use local features for implicit surface regression. Our experimental results show that our IHRPN method performs excellently on the CAPE and AGORA datasets, achieving good performance, and the reconstruction of loose clothing is noticeably more accurate and robust.

RESUMEN

Due to the antiquity and difficulty of excavation, the Terracotta Warriors have suffered varying degrees of damage. To restore the cultural relics to their original appearance, utilizing point clouds to repair damaged Terracotta Warriors has always been a hot topic in cultural relic protection. The output results of existing methods in point cloud completion often lack diversity. Probability-based models represented by Denoising Diffusion Probabilistic Models have recently achieved great success in the field of images and point clouds and can output a variety of results. However, one drawback of diffusion models is that too many samples result in slow generation speed. Toward this issue, we propose a new neural network for Terracotta Warriors fragments completion. During the reverse diffusion stage, we initially decrease the number of sampling steps to generate a coarse result. This preliminary outcome undergoes further refinement through a multi-scale refine network. Additionally, we introduce a novel approach called Partition Attention Sampling to enhance the representation capabilities of features. The effectiveness of the proposed model is validated in the experiments on the real Terracotta Warriors dataset and public dataset. The experimental results conclusively demonstrate that our model exhibits competitive performance in comparison to other existing models.

RESUMEN

Disentanglement research is a critical and important issue in the field of image editing. In order to perform disentangled editing on images generated by generative models, this paper presents an unsupervised, model-agnostic, two-stage trained editing framework. This work addresses the problem of discovering interpretable, disentangled directions of edited image attributes in the latent space of generative models. This effort's primary objective was to address the limitations discovered in previous research, mainly (a) the discovered editing directions are interpretable but significantly entangled, i.e., changes to one attribute affect the others and (b) Prior research has utilized direction discovery and direction disentanglement separately, and they can't work synergistically. More specifically, this paper proposes a two-stage training method that discovers the editing direction with semantics, perturbs the dimension of the direction vector, adjusts it with a penalty mechanism, and makes the editing direction more disentangled. This allows easy distinguishable image editing, such as age and facial expressions in facial images. Experimentally compared to other methods, the proposed method outperforms them both qualitatively and quantitatively in terms of interpretability, disentanglement, and distinguishability of the generated images. The implementation of our method is available at https://github.com/ydniuyongjie/twoStageForFaceEdit.

RESUMEN

Facial approximation (FA) provides a promising means of generating the possible facial appearance of a deceased person. It facilitates exploration of the evolutionary forces driving anatomical changes in ancestral humans and can capture public attention. Despite the recent progress made toward improving the performance of FA methods, a limited understanding of detailed quantitative craniofacial relationships between facial bone and soft tissue morphology may hinder their accuracy, and hence subjective experience and artistic interpretation are required. In this study, we explored craniofacial relationships among human populations based upon average facial soft tissue thickness depths (FSTDs) and covariations between hard and soft tissues of the nose and mouth using geometric morphometrics. Furthermore, we proposed a computerized method to assign the learned craniofacial relationships to generate a probable facial appearance of Homo sapiens, reducing human intervention. A smaller resemblance comparison (an average Procrustes distance was 0.0258 and an average Euclidean distance was 1.79 mm) between approximated and actual faces and a greater recognition rate (91.67%) tested by a face pool indicated that average dense FSTDs contributed to raising the accuracy of approximated faces. Results of partial least squares (PLS) analysis showed that nasal and oral hard tissues have an effect on their soft tissues separately. However, relatively weaker RV correlations (<0.4) and greater approximation errors suggested that we need to be cautious about the accuracy of the approximated nose and mouth soft tissue shapes from bony structures. Overall, the proposed method can facilitate investigations of craniofacial relationships and potentially improve the reliability of the approximated faces for use in numerous applications in forensic science, archaeology, and anthropology.

Asunto(s)

RESUMEN

The dense point clouds of Terracotta Warriors obtained by a 3D scanner have a lot of redundant data, which reduces the efficiency of the transmission and subsequent processing. Aiming at the problems that points generated by sampling methods cannot be learned through the network and are irrelevant to downstream tasks, an end-to-end specific task-driven and learnable down-sampling method named TGPS is proposed. First, the point-based Transformer unit is used to embed the features and the mapping function is used to extract the input point features to dynamically describe the global features. Then, the inner product of the global feature and each point feature is used to estimate the contribution of each point to the global feature. The contribution values are sorted by descending for different tasks, and the point features with high similarity to the global features are retained. To further learn rich local representation, combined with the graph convolution operation, the Dynamic Graph Attention Edge Convolution (DGA EConv) is proposed as a neighborhood graph for local feature aggregation. Finally, the networks for the downstream tasks of point cloud classification and reconstruction are presented. Experiments show that the method realizes the down-sampling under the guidance of the global features. The proposed TGPS-DGA-Net for point cloud classification has achieved the best accuracy on both the real-world Terracotta Warrior fragments and the public datasets.

RESUMEN

The Mexican Hat wavelet (MHW) is strictly derived from the heat kernel by taking its negative first-order derivative with respect to time t. As a solution to the heat equation that the heat kernel has a clear initial condition, the Laplace-Beltrami operator. Although the MHW descriptor can effectively characterize the model information, but it has poor robustness to the model with scale transformation, and the feature description performance is affected to some extent. Following a popular mathematical method, in this paper, we bases on the MHW to study scaling invariance and proposes a new shape descriptor, the scale-invariant Mexican Hat wavelet (SIMHW), which by logarithmic sampling and Fourier transform that obtains the expression of SIMHW in Fourier domain. The experimental results show that SIMHW has finer information description ability and stronger recognition ability, and has better robustness to various non-rigid transformations. It can correctly calculate the similarity between 3D shapes and realize the effective shape retrieval.

RESUMEN

Although many recent deep learning methods have achieved good performance in point cloud analysis, most of them are built upon the heavy cost of manual labeling. Unsupervised representation learning methods have attracted increasing attention due to their high label efficiency. How to learn more useful representations from unlabeled 3D point clouds is still a challenging problem. Addressing this problem, we propose a novel unsupervised learning approach for point cloud analysis, named ULD-Net, consisting of an equivariant-crop (equiv-crop) module to achieve dense similarity learning. We propose dense similarity learning that maximizes consistency across two randomly transformed global-local views at both the instance level and the point level. To build feature correspondence between global and local views, an equiv-crop is proposed to transform features from the global scope to the local scope. Unlike previous methods that require complicated designs, such as negative pairs and momentum encoders, our ULD-Net benefits from the simple Siamese network that relies solely on stop-gradient operation preventing the network from collapsing. We also utilize the feature separability constraint for more representative embeddings. Experimental results show that our ULD-Net achieves the best results of context-based unsupervised methods and comparable performances to supervised models in shape classification and segmentation tasks. On the linear support vector machine classification benchmark, our ULD-Net surpasses the best context-based method spatiotemporal self-supervised representation learning (STRL) by 1.1% overall accuracy. On tasks with fine-tuning, our ULD-Net outperforms STRL under fully supervised and semisupervised settings, in particular, 0.1% accuracy gain on the ModelNet40 classification benchmark, and 0.6% medium intersection of union gain on the ShapeNet part segmentation benchmark.

RESUMEN

The success of deep neural networks usually relies on massive amounts of manually labeled data, which is both expensive and difficult to obtain in many real-world datasets. In this paper, a novel unsupervised representation learning network, UMA-Net, is proposed for the downstream 3D object classification. First, the multi-scale shell-based encoder is proposed, which is able to extract the local features from different scales in a simple yet effective manner. Second, an improved angular loss is presented to get a good metric for measuring the similarity between local features and global representations. Subsequently, the self-reconstruction loss is introduced to ensure the global representations do not deviate from the input data. Additionally, the output point clouds are generated by the proposed cross-dim-based decoder. Finally, a linear classifier is trained using the global representations obtained from the pre-trained model. Furthermore, the performance of this model is evaluated on ModelNet40 and applied to the real-world 3D Terracotta Warriors fragments dataset. Experimental results demonstrate that our model achieves comparable performance and narrows the gap between unsupervised and supervised learning approaches in downstream object classification tasks. Moreover, it is the first attempt to apply the unsupervised representation learning for 3D Terracotta Warriors fragments. We hope this success can provide a new avenue for the virtual protection of cultural relics.

Asunto(s)

RESUMEN

To obtain a higher simplification rate while retaining geometric features, a simplification framework for the point cloud is proposed. Firstly, multi-angle images of the original point cloud are obtained with a virtual camera. Then, feature lines of each image are extracted by deep neural network. Furthermore, according to the proposed mapping relationship between the acquired 2D feature lines and original point cloud, feature points of the point cloud are extracted automatically. Finally, the simplified point cloud is obtained by fusing feature points and simplified non-feature points. The proposed simplification method is applied to four data sets and compared with the other six algorithms. The experimental results demonstrate that our proposed simplification method has the superiority in terms of both retaining geometric features and high simplification rate.

RESUMEN

This study proposes a novel, to the best of our knowledge, transformer-based end-to-end network (TDNet) for point cloud denoising based on encoder-decoder architecture. The encoder is based on the structure of a transformer in natural language processing (NLP). Even though points and sentences are different types of data, the NLP transformer can be improved to be suitable for a point cloud because the point can be regarded as a word. The improved model facilitates point cloud feature extraction and transformation of the input point cloud into the underlying high-dimensional space, which can characterize the semantic relevance between points. Subsequently, the decoder learns the latent manifold of each sampled point from the high-dimensional features obtained by the encoder, finally achieving a clean point cloud. An adaptive sampling approach is introduced during denoising to select points closer to the clean point cloud to reconstruct the surface. This is based on the view that a 3D object is essentially a 2D manifold. Extensive experiments demonstrate that the proposed network is superior in terms of quantitative and qualitative results for synthetic data sets and real-world terracotta warrior fragments.

RESUMEN

BACKGROUND: The development of Cone-beam X-ray luminescence computed tomography (CB-XLCT) has allowed the quantitative in-depth biological imaging, but with a greatly ill-posed and ill-conditioned inverse problem. Although the predefined permissible source region (PSR) is a widely used way to alleviate the problem for CB-XLCT imaging, how to obtain the accurate PSR is still a challenge for the process of inverse reconstruction. METHODS: We proposed an optimized prior knowledge via a sparse non-convex approach (OPK_SNCA) for CB-XLCT imaging. Firstly, non-convex Lp-norm optimization model was employed for copying with the inverse problem, and an iteratively reweighted split augmented lagrangian shrinkage algorithm was developed to obtain a group of sparse solutions based on different non-convex p values. Secondly, a series of permissible regions (PRs) with different discretized mesh was further achieved, and the intersection operation was implemented on the group of PRs to get a reasonable PSR. After that, the final PSR was adopted as an optimized prior knowledge to enhance the reconstruction quality of inverse reconstruction. RESULTS: Both simulation experiments and in vivo experiment were performed to evaluate the efficiency and robustness of the proposed method. CONCLUSIONS: The experimental results demonstrated that our proposed method could significantly improve the imaging quality of the distribution of X-ray-excitable nanophosphors for CB-XLCT.

Asunto(s)

RESUMEN

Automatically selecting a set of representative views of a 3D virtual cultural relic is crucial for constructing wisdom museums. There is no consensus regarding the definition of a good view in computer graphics; the same is true of multiple views. View-based methods play an important role in the field of 3D shape retrieval and classification. However, it is still difficult to select views that not only conform to subjective human preferences but also have a good feature description. In this study, we define two novel measures based on information entropy, named depth variation entropy and depth distribution entropy. These measures were used to determine the amount of information about the depth swings and different depth quantities of each view. Firstly, a canonical pose 3D cultural relic was generated using principal component analysis. A set of depth maps obtained by orthographic cameras was then captured on the dense vertices of a geodesic unit-sphere by subdividing the regular unit-octahedron. Afterwards, the two measures were calculated separately on the depth maps gained from the vertices and the results on each one-eighth sphere form a group. The views with maximum entropy of depth variation and depth distribution were selected, and further scattered viewpoints were selected. Finally, the threshold word histogram derived from the vector quantization of salient local descriptors on the selected depth maps represented the 3D cultural relic. The viewpoints obtained by the proposed method coincided with an arbitrary pose of the 3D model. The latter eliminated the steps of manually adjusting the model's pose and provided acceptable display views for people. In addition, it was verified on several datasets that the proposed method, which uses the Bag-of-Words mechanism and a deep convolution neural network, also has good performance regarding retrieval and classification when dealing with only four views.

RESUMEN

Geometry images parameterise a mesh with a square domain and store the information in a single chart. A one-to-one correspondence between the 2D plane and the 3D model is convenient for processing 3D models. However, the parameterised vertices are not all located at the intersection of the gridlines the existing geometry images. Thus, errors are unavoidable when a 3D mesh is reconstructed from the chart. In this paper, we propose parameterise surface onto a novel geometry image that preserves the constraint of topological neighbourhood information at integer coordinate points on a 2D grid and ensures that the shape of the reconstructed 3D mesh does not change from supplemented image data. We find a collection of edges that opens the mesh into simply connected surface with a single boundary. The point distribution with approximate blue noise spectral characteristics is computed by capacity-constrained delaunay triangulation without retriangulation. We move the vertices to the constrained mesh intersection, adjust the degenerate triangles on a regular grid, and fill the blank part by performing a local affine transformation between each triangle in the mesh and image. Unlike other geometry images, the proposed method results in no error in the reconstructed surface model when floating-point data are stored in the image. High reconstruction accuracy is achieved when the xyz positions are in a 16-bit data format in each image channel because only rounding errors exist in the topology-preserving geometry images, there are no sampling errors. This method performs one-to-one mapping between the 3D surface mesh and the points in the 2D image, while foldovers do not appear in the 2D triangular mesh, maintaining the topological structure. This also shows the potential of using a 2D image processing algorithm to process 3D models.

RESUMEN

The emergence of the three-dimensional (3D) scanner has greatly benefited archeology, which can now store cultural heritage artifacts in computers and present them on the Internet. As many Terracotta Warriors have been predominantly found in fragments, the pre-processing of these fragments is very important. The raw point cloud of the fragments has lots of redundant points; it requires an excessively large storage space and much time for post-processing. Thus, an effective method for point cloud simplification is proposed for 3D Terracotta Warrior fragments. First, an algorithm for extracting feature points is proposed that is based on local structure. By constructing a k-dimension tree to establish the k-nearest neighborhood of the point cloud, and comparing the feature discriminant parameter and characteristic threshold, the feature points, as well as the non-feature points, are separated. Second, a deep neural network is constructed to simplify the non-feature points. Finally, the feature points and the simplified non-feature points are merged to form the complete simplified point cloud. Experiments with the public point cloud data and the real-world Terracotta Warrior fragments data are designed and conducted. Excellent simplification results were obtained, indicating that the geometric feature can be preserved very well.

RESUMEN

Cone-beam X-ray luminescence computed tomography (CB-XLCT) emerged as a novel hybrid technique for early detection of small tumors in vivo. However, severe ill-posedness is still a challenge for CB-XLCT imaging. In this study, an adaptive shrinking reconstruction framework without a prior information is proposed for CB-XLCT. In reconstruction processing, the mesh nodes are automatically selected with higher probability to contribute to the distribution of target for imaging. Specially, an adaptive shrinking function is designed to automatically control the permissible source region at a multi-scale rate. Both 3D digital mouse and in vivo experiments were carried out to test the performance of our method. The results indicate that the proposed framework can dramatically improve the imaging quality of CB-XLCT.

RESUMEN

Skull sex estimation is one of the hot research topics in forensic anthropology, and has important research value in the fields of criminal investigation, archeology, anthropology, and so on. Sex estimation of skull is crucial in forensic investigations, whether in legal situations that involve living people or to identify mortal remains. The aim of this study is to establish a skull-based sex estimation model in Chinese population, providing a scientific reference for the practical application of forensic medicine and anthropology. We take the superior orbital margin and frontal bone of the skull as the research object and proposed a technology of objective sex estimation of the skull using wavelet transform and Fourier transform. Firstly, the supraorbital margin and frontal bone were quantified by wavelet transform and Fourier transform, and then the extracted features were classified by SVM, and the model was tested. The experimental results show that the accuracy rate of male and female sex discrimination is 90.9% and 94.4%, respectively, which is higher than that of morphological and measurement methods. Compared with the traditional methods, the method has more theoretical basis and objectivity, and the correct rate is higher.

Asunto(s)

RESUMEN

OBJECTIVE: To evaluate the midterm results of the cementless S-ROM modular femoral stem used with subtrochanteric transverse shortening osteotomy for the treatment of high hip dislocation secondary to hip pyogenic arthritis. METHODS: We retrospectively reviewed the data of 49 patients (49 hips) with an average infection quiescent period of 37.4 years who underwent cementless total hip arthroplasty (THA) with simultaneous subtrochanteric transverse shortening osteotomy from July 2008 to June 2012. There were 23 men and 26 women with a mean age of 44.3 years at the time of surgery. The following clinical outcomes were evaluated: the Western Ontario and McMaster Universities Arthritis Index (WOMAC) score, Harris hip score (HSS), modified Merle d'Aubigne-Postel hip (MAP) score, low back pain visual analog scale score, 12-item short-form health survey questionnaire score, limp, and Trendelenburg sign. Radiographic outcomes and complications were also evaluated. RESULTS: The mean follow-up period was 8.7 years (range, 5.5-10 years). No infection recurrence was observed after THA. The average HSS significantly improved from 45.0 to 84.8. The WOMAC score improved from 70.1 ± 3.5 (range, 65-76) to 43.1 ± 13.4 (range, 21-67). The modified MAP score improved from 5.9 ± 1.9 (range, 3-9) to 14.3 ± 2.4 (range, 11-18). The low back pain visual analog scale score, 12-item short-form health survey questionnaire score, limp, and Trendelenburg sign also improved significantly. The average limb length discrepancy decreased from 39.6 mm (range, 30-55 mm) to 7.2 mm (range, 0-22 mm). Two patients had temporary sciatic nerve paralysis but recovered within 6 months without any functional defects; one had an intraoperative fracture fixed by cerclage wires. One hip required revision surgery because of femoral stem aseptic loosening. CONCLUSIONS: The cementless S-ROM modular femoral stem used with subtrochanteric transverse shortening osteotomy is safe and effective for high hip dislocation secondary to pyogenic arthritis and provides satisfactory midterm results. Significant improvements in clinical function were observed, as were high rates of stable fixation of the cementless implant, restoration of more normal limb lengths, and a low incidence of complications.

Asunto(s)

RESUMEN

Previous studies have used principal component analysis (PCA) to investigate the craniofacial relationship, as well as sex determination using facial factors. However, few studies have investigated the extent to which the choice of principal components (PCs) affects the analysis of craniofacial relationship and sexual dimorphism. In this paper, we propose a PCA-based method for visual and quantitative analysis, using 140 samples of 3D heads (70 male and 70 female), produced from computed tomography (CT) images. There are two parts to the method. First, skull and facial landmarks are manually marked to guide the model's registration so that dense corresponding vertices occupy the same relative position in every sample. Statistical shape spaces of the skull and face in dense corresponding vertices are constructed using PCA. Variations in these vertices, captured in every principal component (PC), are visualized to observe shape variability. The correlations of skull- and face-based PC scores are analysed, and linear regression is used to fit the craniofacial relationship. We compute the PC coefficients of a face based on this craniofacial relationship and the PC scores of a skull, and apply the coefficients to estimate a 3D face for the skull. To evaluate the accuracy of the computed craniofacial relationship, the mean and standard deviation of every vertex between the two models are computed, where these models are reconstructed using real PC scores and coefficients. Second, each PC in facial space is analysed for sex determination, for which support vector machines (SVMs) are used. We examined the correlation between PCs and sex, and explored the extent to which the choice of PCs affects the expression of sexual dimorphism. Our results suggest that skull- and face-based PCs can be used to describe the craniofacial relationship and that the accuracy of the method can be improved by using an increased number of face-based PCs. The results show that the accuracy of the sex classification is related to the choice of PCs. The highest sex classification rate is 91.43% using our method.

Asunto(s)

RESUMEN

The computer-aided craniofacial reconstruction (CFR) technique has been widely used in the fields of criminal investigation, archaeology, anthropology and cosmetic surgery. The evaluation of craniofacial reconstruction results is important for improving the effect of craniofacial reconstruction. Here, we used the sparse principal component analysis (SPCA) method to evaluate the similarity between two sets of craniofacial data. Compared with principal component analysis (PCA), SPCA can effectively reduce the dimensionality and simultaneously produce sparse principal components with sparse loadings, thus making it easy to explain the results. The experimental results indicated that the evaluation results of PCA and SPCA are consistent to a large extent. To compare the inconsistent results, we performed a subjective test, which indicated that the result of SPCA is superior to that of PCA. Most importantly, SPCA can not only compare the similarity of two craniofacial datasets but also locate regions of high similarity, which is important for improving the craniofacial reconstruction effect. In addition, the areas or features that are important for craniofacial similarity measurements can be determined from a large amount of data. We conclude that the craniofacial contour is the most important factor in craniofacial similarity evaluation. This conclusion is consistent with the conclusions of psychological experiments on face recognition and our subjective test. The results may provide important guidance for three- or two-dimensional face similarity evaluation, analysis and face recognition.

Asunto(s)

RESUMEN

PURPOSE: Virtual digital resources and printed models have become indispensable tools for medical training and surgical planning. Nevertheless, printed models of soft tissue organs are still challenging to reproduce. This study adopts open source packages and a low-cost desktop 3D printer to convert multiple modalities of medical images to digital resources (volume rendering images and digital models) and lifelike printed models, which are useful to enhance our understanding of the geometric structure and complex spatial nature of anatomical organs. MATERIALS AND METHODS: Neuroimaging technologies such as CT, CTA, MRI, and TOF-MRA collect serial medical images. The procedures for producing digital resources can be divided into volume rendering and medical image reconstruction. To verify the accuracy of reconstruction, this study presents qualitative and quantitative assessments. Subsequently, digital models are archived as stereolithography format files and imported to the bundled software of the 3D printer. The printed models are produced using polylactide filament materials. RESULTS: We have successfully converted multiple modalities of medical images to digital resources and printed models for both hard organs (cranial base and tooth) and soft tissue organs (brain, blood vessels of the brain, the heart chambers and vessel lumen, and pituitary tumor). Multiple digital resources and printed models were provided to illustrate the anatomical relationship between organs and complicated surrounding structures. Three-dimensional printing (3DP) is a powerful tool to produce lifelike and tangible models. CONCLUSIONS: We present an available and cost-effective method for producing both digital resources and printed models. The choice of modality in medical images and the processing approach is important when reproducing soft tissue organs models. The accuracy of the printed model is determined by the quality of organ models and 3DP. With the ongoing improvement of printing techniques and the variety of materials available, 3DP will become an indispensable tool in medical training and surgical planning.

Asunto(s)