Marked methylation changes in intestinal genes during the perinatal period of preterm neonates.

BACKGROUND: The serious feeding- and microbiota-associated intestinal disease, necrotizing enterocolitis (NEC), occurs mainly in infants born prematurely (5-10% of all newborns) and most frequently after formula-feeding. We hypothesized that changes in gene methylation is involved in the prenatal maturation of the intestine and its response to the first days of formula feeding, potentially leading to NEC in preterm pigs used as models for preterm infants. RESULTS: Reduced Representation Bisulfite Sequencing (RRBS) was used to assess if changes in intestinal DNA methylation are associated with formula-induced NEC outbreak and advancing age from 10 days before birth to 4 days after birth. Selected key genes with differentially methylated gene regions (DMRs) between groups were further validated by HiSeq-based bisulfite sequencing PCR and RT-qPCR to assess methylation and expression levels. Consistent with the maturation of many intestinal functions in the perinatal period, methylation level of most genes decreased with advancing pre- and postnatal age. The highest number of DMRs was identified between the newborn and 4 d-old preterm pigs. There were few intestinal DMR differences between unaffected pigs and pigs with initial evidence of NEC. In the 4 d-old formula-fed preterm pigs, four genes associated with intestinal metabolism (CYP2W1, GPR146, TOP1MT, CEND1) showed significant hyper-methylation in their promoter CGIs, and thus, down-regulated transcription. Methylation-driven down-regulation of such genes may predispose the immature intestine to later metabolic dysfunctions and severe NEC lesions. CONCLUSIONS: Pre- and postnatal changes in intestinal DNA methylation may contribute to high NEC sensitivity in preterm neonates. Optimizing gene methylation changes via environmental stimuli (e.g. diet, nutrition, gut microbiota), may help to make immature newborn infants more resistant to gut dysfunctions, both short and long term.

Neural-ABC: Neural Parametric Models for Articulated Body With Clothes.

In this paper, we introduce Neural-ABC, a novel parametric model based on neural implicit functions that can represent clothed human bodies with disentangled latent spaces for identity, clothing, shape, and pose. Traditional mesh-based representations struggle to represent articulated bodies with clothes due to the diversity of human body shapes and clothing styles, as well as the complexity of poses. Our proposed model provides a unified framework for parametric modeling, which can represent the identity, clothing, shape and pose of the clothed human body. Our proposed approach utilizes the power of neural implicit functions as the underlying representation and integrates well-designed structures to meet the necessary requirements. Specifically, we represent the underlying body as a signed distance function and clothing as an unsigned distance function, and they can be uniformly represented as unsigned distance fields. Different types of clothing do not require predefined topological structures or classifications, and can follow changes in the underlying body to fit the body. Additionally, we construct poses using a controllable articulated structure. The model is trained on both open and newly constructed datasets, and our decoupling strategy is carefully designed to ensure optimal performance. Our model excels at disentangling clothing and identity in different shape and poses while preserving the style of the clothing. We demonstrate that Neural-ABC fits new observations of different types of clothing. Compared to other state-of-the-art parametric models, Neural-ABC demonstrates powerful advantages in the reconstruction of clothed human bodies, as evidenced by fitting raw scans, depth maps and images. We show that the attributes of the fitted results can be further edited by adjusting their identities, clothing, shape and pose codes. The dataset and trained parametric model will be available at https://ustc3dv.github.io/NeuralABC/.

A Closer Look at the Reflection Formulation in Single Image Reflection Removal.

How to model the effect of reflection is crucial for single image reflection removal (SIRR) task. Modern SIRR methods usually simplify the reflection formulation with the assumption of linear combination of a transmission layer and a reflection layer. However, the large variations in image content and the real-world picture-taking conditions often result in far more complex reflection. In this paper, we introduce a new screen-blur combination based on two important factors, namely the intensity and the blurriness of reflection, to better characterize the reflection formulation in SIRR. Specifically, we present Screen-blur Reflection Networks (SRNet), which executes the screen-blur formulation in its network design and adapts to the complex reflection on real scenes. Technically, SRNet consists of three components: a blended image generator, a reflection estimator and a reflection removal module. The image generator exploits the screen-blur combination to synthesize the training blended images. The reflection estimator learns the reflection layer and a blur degree that measures the level of blurriness for reflection. The reflection removal module further uses the blended image, blur degree and reflection layer to filter out the transmission layer in a cascaded manner. Superior results on three different SIRR methods are reported when generating the training data on the principle of the screen-blur combination. Moreover, extensive experiments on six datasets quantitatively and qualitatively demonstrate the efficacy of SRNet over the state-of-the-art methods.

Fast and Robust Non-Rigid Registration Using Accelerated Majorization-Minimization.

Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typically adopt the lp type robust norm to measure the alignment error and regularize the smoothness of deformation, and use a proximal algorithm to solve the resulting non-smooth optimization problem. However, the slow convergence of such algorithms limits their wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps. The problem is solved using the majorization-minimization algorithm, which reduces each iteration to a convex quadratic problem with a closed-form solution. We further apply Anderson acceleration to speed up the convergence of the solver, enabling the solver to run efficiently on devices with limited compute capability. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlaps, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://github.com/yaoyx689/AMM_NRR.

Robust Mesh Representation Learning via Efficient Local Structure-Aware Anisotropic Convolution.

Mesh is a type of data structure commonly used for 3-D shapes. Representation learning for 3-D meshes is essential in many computer vision and graphics applications. The recent success of convolutional neural networks (CNNs) for structured data (e.g., images) suggests the value of adapting insights from CNN for 3-D shapes. However, 3-D shape data are irregular since each node's neighbors are unordered. Various graph neural networks for 3-D shapes have been developed with isotropic filters or predefined local coordinate systems to overcome the node inconsistency on graphs. However, isotropic filters or predefined local coordinate systems limit the representation power. In this article, we propose a local structure-aware anisotropic convolutional operation (LSA-Conv) that learns adaptive weighting matrices for each template's node according to its neighboring structure and performs shared anisotropic filters. In fact, the learnable weighting matrix is similar to the attention matrix in the random synthesizer-a new Transformer model for natural language processing (NLP). Since the learnable weighting matrices require large amounts of parameters for high-resolution 3-D shapes, we introduce a matrix factorization technique to notably reduce the parameter size, denoted as LSA-small. Furthermore, a residual connection with a linear transformation is introduced to improve the performance of our LSA-Conv. Comprehensive experiments demonstrate that our model produces significant improvement in 3-D shape reconstruction compared to state-of-the-art methods.

Sketch2PQ: Freeform Planar Quadrilateral Mesh Design via a Single Sketch.

The freeform architectural modeling process often involves two important stages: concept design and digital modeling. In the first stage, architects usually sketch the overall 3D shape and the panel layout on a physical or digital paper briefly. In the second stage, a digital 3D model is created using the sketch as a reference. The digital model needs to incorporate geometric requirements for its components, such as the planarity of panels due to consideration of construction costs, which can make the modeling process more challenging. In this work, we present a novel sketch-based system to bridge the concept design and digital modeling of freeform roof-like shapes represented as planar quadrilateral (PQ) meshes. Our system allows the user to sketch the surface boundary and contour lines under axonometric projection and supports the sketching of occluded regions. In addition, the user can sketch feature lines to provide directional guidance to the PQ mesh layout. Given the 2D sketch input, we propose a deep neural network to infer in real-time the underlying surface shape along with a dense conjugate direction field, both of which are used to extract the final PQ mesh. To train and validate our network, we generate a large synthetic dataset that mimics architect sketching of freeform quadrilateral patches. The effectiveness and usability of our system are demonstrated with quantitative and qualitative evaluation as well as user studies.

IntrinsicNGP: Intrinsic Coordinate based Hash Encoding for Human NeRF.

Recently, many works have been proposed to utilize the neural radiance field for novel view synthesis of human performers. However, most of these methods require hours of training, making them difficult for practical use. To address this challenging problem, we propose IntrinsicNGP, which can train from scratch and achieve high-fidelity results in few minutes with videos of a human performer. To achieve this target, we introduce a continuous and optimizable intrinsic coordinate rather than the original explicit Euclidean coordinate in the hash encoding module of instant-NGP. With this novel intrinsic coordinate, IntrinsicNGP can aggregate inter-frame information for dynamic objects with the help of proxy geometry shapes. Moreover, the results trained with the given rough geometry shapes can be further refined with an optimizable offset field based on the intrinsic coordinate. Extensive experimental results on several datasets demonstrate the effectiveness and efficiency of IntrinsicNGP. We also illustrate our approach's ability to edit the shape of reconstructed subjects.

Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis.

Point clouds are characterized by irregularity and unstructuredness, which pose challenges in efficient data exploitation and discriminative feature extraction. In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels. Intuitively, Flattening-Net implicitly approximates a locally smooth 3D-to-2D surface flattening process while effectively preserving neighborhood consistency. As a generic representation modality, PGI inherently encodes the intrinsic property of the underlying manifold structure and facilitates surface-style point feature aggregation. To demonstrate its potential, we construct a unified learning framework directly operating on PGIs to achieve diverse types of high-level and low-level downstream applications driven by specific task networks, including classification, segmentation, reconstruction, and upsampling. Extensive experiments demonstrate that our methods perform favorably against the current state-of-the-art competitors.

Experimental and Simulation Study on Welding Characteristics and Parameters of Gas Metal Arc Welding for Q345qD Thick-Plate Steel.

The welding and construction processes for H-type thick-plate bridge steel involve complex multi-pass welding processes, which make it difficult to ensure its welding performance. Accordingly, it is crucial to explore the inherent correlations between the welding process parameters and welding quality, and apply them to welding robots, eliminating the instability in manual welding. In order to improve welding quality, the GMAW (gas metal arc welding) welding process parameters are simulated, using the Q345qD bridge steel flat joint model. Four welds with X-shaped grooves are designed to optimize the parameters of the welding current, welding voltage, and welding speed. The optimal welding process parameters are investigated through thermal-elastic-plastic simulation analysis and experimental verification. The results indicate that, when the welding current is set to 230 A, the welding voltage to 32 V, and the welding speed to 0.003 m/s, the maximum deformation of the welded plate is 0.52 mm, with a maximum welding residual stress of 345 MPa. Both the simulation results of multi-pass welding, and the experimental tests meet the welding requirements, as they show no excessive stress or strain. These parameters can be applied to building large steel-frame bridges using welding robots, improving the quality of welded joints.

3D-CariGAN: An End-to-End Solution to 3D Caricature Generation From Normal Face Photos.

Caricature is a type of artistic style of human faces that attracts considerable attention in the entertainment industry. So far a few 3D caricature generation methods exist and all of them require some caricature information (e.g., a caricature sketch or 2D caricature) as input. This kind of input, however, is difficult to provide by non-professional users. In this paper, we propose an end-to-end deep neural network model that generates high-quality 3D caricatures directly from a normal 2D face photo. The most challenging issue for our system is that the source domain of face photos (characterized by normal 2D faces) is significantly different from the target domain of 3D caricatures (characterized by 3D exaggerated face shapes and textures). To address this challenge, we: (1) build a large dataset of 5,343 3D caricature meshes and use it to establish a PCA model in the 3D caricature shape space; (2) reconstruct a normal full 3D head from the input face photo and use its PCA representation in the 3D caricature shape space to establish correspondences between the input photo and 3D caricature shape; and (3) propose a novel character loss and a novel caricature loss based on previous psychological studies on caricatures. Experiments including a novel two-level user study show that our system can generate high-quality 3D caricatures directly from normal face photos.

Facial Expression Retargeting From Human to Avatar Made Easy.

Facial expression retargeting from humans to virtual characters is a useful technique in computer graphics and animation. Traditional methods use markers or blendshapes to construct a mapping between the human and avatar faces. However, these approaches require a tedious 3D modeling process, and the performance relies on the modelers' experience. In this article, we propose a brand-new solution to this cross-domain expression transfer problem via nonlinear expression embedding and expression domain translation. We first build low-dimensional latent spaces for the human and avatar facial expressions with variational autoencoder. Then we construct correspondences between the two latent spaces guided by geometric and perceptual constraints. Specifically, we design geometric correspondences to reflect geometric matching and utilize a triplet data structure to express users' perceptual preference of avatar expressions. A user-friendly method is proposed to automatically generate triplets for a system allowing users to easily and efficiently annotate the correspondences. Using both geometric and perceptual correspondences, we trained a network for expression domain translation from human to avatar. Extensive experimental results and user studies demonstrate that even nonprofessional users can apply our method to generate high-quality facial expression retargeting results with less time and effort.

Fast and Robust Iterative Closest Point.

The iterative closest point (ICP) algorithm and its variants are a fundamental technique for rigid registration between two point sets, with wide applications in different areas from robotics to 3D reconstruction. The main drawbacks for ICP are its slow convergence, as well as its sensitivity to outliers, missing data, and partial overlaps. Recent work such as Sparse ICP achieves robustness via sparsity optimization at the cost of computational speed. In this paper, we propose a new method for robust registration with fast convergence. First, we show that the classical point-to-point ICP can be treated as a majorization-minimization (MM) algorithm, and propose an Anderson acceleration approach to speed up its convergence. In addition, we introduce a robust error metric based on the Welsch's function, which is minimized efficiently using the MM algorithm with Anderson acceleration. On challenging datasets with noises and partial overlaps, we achieve similar or better accuracy than Sparse ICP while being at least an order of magnitude faster. Finally, we extend the robust formulation to point-to-plane ICP, and solve the resulting problem using a similar Anderson-accelerated MM strategy. Our robust ICP methods improve the registration accuracy on benchmark datasets while being competitive in computational time.

GDR-Net: A Geometric Detail Recovering Network for 3D Scanned Objects.

This article addresses the problem of mesh super-resolution such that the geometry details which are not well represented in the low-resolution models can be recovered and well represented in the generated high-quality models. The main challenges of this problem are the nonregularity of 3D mesh representation and the high complexity of 3D shapes. We propose a deep neural network called GDR-Net to solve this ill-posed problem, which resolves the two challenges simultaneously. First, to overcome the nonregularity, we regress a displacement in radial basis function parameter space instead of the vertex-wise coordinates in the euclidean space. Second, to overcome the high complexity, we apply the detail recovery process to small surface patches extracted from the input surface and obtain the overall high-quality mesh by fusing the refined surface patches. To train the network, we constructed a dataset composed of both real-world and synthetic scanned models, including high/low-quality pairs. Our experimental results demonstrate that GDR-Net works well for general models and outperforms previous methods for recovering geometric details.

GeodesicEmbedding (GE): A High-Dimensional Embedding Approach for Fast Geodesic Distance Queries.

In this article, we develop a novel method for fast geodesic distance queries. The key idea is to embed the mesh into a high-dimensional space, such that the euclidean distance in the high-dimensional space can induce the geodesic distance in the original manifold surface. However, directly solving the high-dimensional embedding problem is not feasible due to the large number of variables and the fact that the embedding problem is highly nonlinear. We overcome the challenges with two novel ideas. First, instead of taking all vertices as variables, we embed only the saddle vertices, which greatly reduces the problem complexity. We then compute a local embedding for each non-saddle vertex. Second, to reduce the large approximation error resulting from the purely euclidean embedding, we propose a cascaded optimization approach that repeatedly introduces additional embedding coordinates with a non-euclidean function to reduce the approximation residual. Using the precomputation data, our approach can determine the geodesic distance between any two vertices in near-constant time. Computational testing results show that our method is more desirable than previous geodesic distance queries methods.

3D Face From X: Learning Face Shape From Diverse Sources.

We present a novel method to jointly learn a 3D face parametric model and 3D face reconstruction from diverse sources. Previous methods usually learn 3D face modeling from one kind of source, such as scanned data or in-the-wild images. Although 3D scanned data contain accurate geometric information of face shapes, the capture system is expensive and such datasets usually contain a small number of subjects. On the other hand, in-the-wild face images are easily obtained and there are a large number of facial images. However, facial images do not contain explicit geometric information. In this paper, we propose a method to learn a unified face model from diverse sources. Besides scanned face data and face images, we also utilize a large number of RGB-D images captured with an iPhone X to bridge the gap between the two sources. Experimental results demonstrate that with training data from more sources, we can learn a more powerful face model.

Parallel and Scalable Heat Methods for Geodesic Distance Computation.

In this paper, we propose a parallel and scalable approach for geodesic distance computation on triangle meshes. Our key observation is that the recovery of geodesic distance with the heat method [1] can be reformulated as optimization of its gradients subject to integrability, which can be solved using an efficient first-order method that requires no linear system solving and converges quickly. Afterward, the geodesic distance is efficiently recovered by parallel integration of the optimized gradients in breadth-first order. Moreover, we employ a similar breadth-first strategy to derive a parallel Gauss-Seidel solver for the diffusion step in the heat method. To further lower the memory consumption from gradient optimization on faces, we also propose a formulation that optimizes the projected gradients on edges, which reduces the memory footprint by about 50 percent. Our approach is trivially parallelizable, with a low memory footprint that grows linearly with respect to the model size. This makes it particularly suitable for handling large models. Experimental results show that it can efficiently compute geodesic distance on meshes with more than 200 million vertices on a desktop PC with 128 GB RAM, outperforming the original heat method and other state-of-the-art geodesic distance solvers.

Poisson Vector Graphics (PVG)-Guided Face Color Transfer in Videos.

This article presents a simple yet effective algorithm for automatically transferring face colors in portrait videos. We extract the facial features and vectorize the faces in the input video using Poisson vector graphics, which encodes the low-frequency colors as the boundary colors of diffusion curves, and the high-frequency colors as Poisson regions. Then, we transfer the face color of a reference image/video to the first frame of the input video by applying optimal mass transport between the boundary colors of diffusion curves. Next the boundary color of the first frame is transferred to the subsequent frames by matching the curves. Finally, with the original or modified Poisson regions, we render the video using an efficient random-access Poisson solver. Thanks to our efficient diffusion curve matching algorithm, transferring colors for the vectorized video takes less than 1 millisecond per frame. Our method is particularly desired for frequent transfer from multiple references due to its information reuse nature. The simple diffusion curve matching also greatly improves the performance of video vectorization, since we only need to solve an optimization problem for the first frame. Since our method does not require correspondence between the reference image/video and the input video, it is flexible and robust to handle faces with significantly different geometries and postures, which often pose challenges to the existing methods. Moreover, by manipulating Poisson regions, we can enhance or reduce the highlight and contrast so that the reference color can fit into the input video naturally. We demonstrate the efficacy of our method on image-to-video transfer and color swap in videos.

The evolutionarily dynamic IFN-inducible GTPase proteins play conserved immune functions in vertebrates and cephalochordates.

Interferon (IFN)-inducible GTPases currently include four families of proteins: myxovirus resistant proteins (Mxs), guanylate-binding proteins (GBPs), immunity-related GTPase proteins (IRGs), and very large inducible GTPase proteins (VLIGs). They are all under conserved regulation by IFNs in humans and mice and play a critical role in preventing microbial infections. However, differences between vertebrates are poorly characterized, and their evolutionary origins have not been studied in detail. In this study, we performed comparative genomic analysis of the four families in 18 representative animals that yielded several unexpected results. Firstly, we found that Mx, GBP, and IRG protein families arose before the divergence of chordate subphyla, but VLIG emerged solely in vertebrates. Secondly, IRG, GBP, and VLIG families have experienced a high rate of gene gain and loss during the evolution, with the GBP family being lost entirely in two pufferfish and VLIG family lost in primates and carnivores. Thirdly, the regulation of these genes by IFNs is highly conserved throughout vertebrates although the VLIG protein sequences in fish have lost the first 870 amino acid residues. Finally, amphioxus IFN-inducible GTPase genes are all highly expressed in immune-related organs such as gill, liver, and intestine and are upregulated after challenge with PolyI:C and pathogens, although no IFNs or their receptors were detected in the current amphioxus genome database. These results suggest that IFN-inducible GTPase genes play conserved immune functions both in vertebrates and in cephalochordates.

[Construction of genome BAC library for single Branchiostoma belcheri individual].

As one of the closest living invertebrate relatives of vertebrates, amphioxus (subphylum Cephalochordata) occupies a key position in animal evolution and is becoming the best available proxy and model animal for studying the last common ancestor of all chordates, especially vertebrates. As long-term continuous culturing of amphioxus in laboratory became reliable, for pushing this animal to be a more successful model system, whole-genome sequencing of one or more species derived from this branch will be another urgent issue needed to address. In the present study, we described the construction and characterization of a bacterial artificial chromosome (BAC) library, using a single individual of Chinese amphioxus (Branchiostoma belcheri). High quality genomic DNA extracted from the spermary was partially digested with EcoRand EcoRmethylase. Desirable DNA fragments were isolated by pulsed field gel electrophoresis (PFGE), ligated to linearized and phosphorylased carrier pCC1BAC, and then transformed to Escherichia coli EPI300. The constructed library consists of 44 706 clones with the average insert fragment size around 80 kb as estimated by PFGE. The representation of the library is about 9 equivalents to the amhioxus genome. These results indicate that the BAC library will be useful for functional genomic studies and facilitate the whole-genome sequencing of Chinese amphioxus.

Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network.

Human bodies exhibit various shapes for different identities or poses, but the body shape has certain similarities in structure and thus can be embedded in a low-dimensional space. This article presents an autoencoder-like network architecture to learn disentangled shape and pose embedding specifically for the 3D human body. This is inspired by recent progress of deformation-based latent representation learning. To improve the reconstruction accuracy, we propose a hierarchical reconstruction pipeline for the disentangling process and construct a large dataset of human body models with consistent connectivity for the learning of the neural network. Our learned embedding can not only achieve superior reconstruction accuracy but also provide great flexibility in 3D human body generation via interpolation, bilinear interpolation, and latent space sampling. The results from extensive experiments demonstrate the powerfulness of our learned 3D human body embedding in various applications.