3D Gaussian Splatting has the capability for realtime and high-quality scene reconstruction, bringing the efficiency and accuracy of this task to a new level. Most previous methods improve the vanilla 3DGS by incorporating external priors such as depth priors and shape priors. However, these methods often suffer from high memory cost, distorted geometric structures, and limitations in scene density. To solve these issues, this paper proposes a new 3DGS-based method for scene reconstruction, showing stable reconstruction and better geometry in both dense and sparse scenes. We re-model the growing of the Gaussians as a bi-directional process without any external priors, adaptively increasing and decreasing the density of the Gaussians across various scenes. For this purpose, we introduce a bi-directional Gaussian growing mechanism that determines the cloning, splitting and merging operations based on the region consistency within a local receptive field. We utilize these three operations to enable adaptive bi-directional control of the density of the Gaussian points across different regions, effectively improving the geometric structure and simplifying the Gaussian points. Extensive experiments on several open benchmarks have demonstrated that our method could universally achieve comparable results with much fewer Gaussian points and better geometry structures in both dense and sparse scenes with a concise framework. We will release our codes after this paper is accepted.

Tooth arrangement is an essential step in the digital orthodontic planning process. Existing learning-based methods use hidden teeth features to directly regress teeth motions, which couples target pose perception and motion regression. It could lead to poor perceptions of three-dimensional transformation. They also ignore the possible overlaps or gaps between teeth of predicted dentition, which is generally unacceptable. Therefore, we propose DTAN, a differentiable collision-supervised tooth arrangement network, decoupling predicting tasks and feature modeling. DTAN decouples the tooth arrangement task by first predicting the hidden features of the final teeth poses and then using them to assist in regressing the motions between the beginning and target teeth. To learn the hidden features better, DTAN also decouples the teeth-hidden features into geometric and positional features, which are further supervised by feature consistency constraints. Furthermore, we propose a novel differentiable collision loss function for point cloud data to constrain the related gestures between teeth, which can be easily extended to other 3D point cloud tasks. We propose an arch-width guided tooth arrangement network, named C-DTAN, to make the results controllable. We construct three different tooth arrangement datasets and achieve drastically improved performance on accuracy and speed compared with existing methods.

Human scene interaction (HSI) aims to understand and accommodate the various ways humans interact with their environment. However, existing works typically struggle to produce high-precision contact estimation for understanding these interactions and lack sufficient fine-grained semantics to adapt to the complexities of diverse characters and scenes, resulting in unnatural and inaccurate interacting motions. In this paper, we present a novel approach to automatic human scene interaction that effectively recovers the human body mesh and high-precision contact information, subsequently enabling adaptation to different environments. Our main contributions include the proposal of a contact estimation framework that leverages semantic features from 2D images and 3D model recovered with inverse kinematics to guide the learning of vertex-level human scene contact (HSC) estimation. For motion adaptation, we propose an enhanced Laplacian semantics descriptor combined with kinematic constraints, enabling precise retargeting between variously sized human models and distinct 3D scenes. Through extensive experiments, we demonstrate our method's superiority against state-of-the-art approaches and showcase the results of the automatic human scene interaction process.

Photo collage aims to automatically arrange multiple photos on a given canvas with high aesthetic quality. Existing methods are based mainly on handcrafted feature optimization, which cannot adequately capture high-level human aesthetic senses. Deep learning provides a promising way, but owing to the complexity of collage and lack of training data, a solution has yet to be found. In this paper, we propose a novel pipeline for automatic generation of aspect ratio specified collage and the reinforcement learning technique is introduced in non-content-preserving collage. Inspired by manual collages, we model the collage generation as a sequential decision process to adjust spatial positions, orientation angles, placement order and the global layout. To instruct the agent to improve both the overall layout and local details, the reward function is specially designed for collage, considering subjective and objective factors. To overcome the lack of training data, we pretrain our deep aesthetic network on a large scale image aesthetic dataset (CPC) for general aesthetic feature extraction and propose an attention fusion module for structural collage feature representation. We test our model against competing methods on movie and image datasets and our results outperform others in several quality evaluations. Further user studies are also conducted to demonstrate the effectiveness.

Ensemble simulation is a crucial method to handle potential uncertainty in modern simulation and has been widely applied in many disciplines. Many ensemble contour visualization methods have been introduced to facilitate ensemble data analysis. On the basis of deep exploration and summarization of existing techniques and domain requirements, we propose a unified framework of ensemble contour visualization, EnConVis (Ensemble Contour Visualization), which systematically combines state-of-the-art methods. We model ensemble contour visualization as a four-step pipeline consisting of four essential procedures: member filtering, point-wise modeling, uncertainty band extraction, and visual mapping. For each of the four essential procedures, we compare different methods they use, analyze their pros and cons, highlight research gaps, and attempt to fill them. Specifically, we add Kernel Density Estimation in the point-wise modeling procedure and multi-layer extraction in the uncertainty band extraction procedure. This step shows the ensemble data's details accurately and provides abstract levels. We also analyze existing methods from a global perspective. We investigate their mechanisms and compare their effects, on the basis of which, we offer selection guidelines for them. From the overall perspective of this framework, we find choices and combinations that have not been tried before, which can be well compensated by our method. Synthetic data and real-world data are leveraged to verify the efficacy of our method. Domain experts' feedback suggests that our approach helps them better understand ensemble data analysis.

Image collage task aims to create an informative and visual-aesthetic visual summarization for an image collection. While several recent works exploit tree-based algorithm to preserve image content better, all of them resort to hand-crafted adjustment rules to optimize the collage tree structure, leading to the failure of fully exploring the structure space of collage tree. Our key idea is to soften the discrete tree structure space into a continuous probability space. We propose SoftCollage, a novel method that employs a neural-based differentiable probabilistic tree generator to produce the probability distribution of correlation-preserving collage tree conditioned on deep image feature, aspect ratio and canvas size. The differentiable characteristic allows us to formulate the tree-based collage generation as a differentiable process and directly exploit gradient to optimize the collage layout in the level of probability space in an end-to-end manner. To facilitate image collage research, we propose AIC, a large-scale public-available annotated dataset for image collage evaluation. Extensive experiments on the introduced dataset demonstrate the superior performance of the proposed method. Data and codes are available at https://github.com/ChineseYjh/SoftCollage.

Biases inevitably occur in numerical weather prediction (NWP) due to an idealized numerical assumption for modeling chaotic atmospheric systems. Therefore, the rapid and accurate identification and calibration of biases is crucial for NWP in weather forecasting. Conventional approaches, such as various analog post-processing forecast methods, have been designed to aid in bias calibration. However, these approaches fail to consider the spatiotemporal correlations of forecast bias, which can considerably affect calibration efficacy. In this article, we propose a novel bias pattern extraction approach based on forecasting-observation probability density by merging historical forecasting and observation datasets. Given a spatiotemporal scope, our approach extracts and fuses bias patterns and automatically divides regions with similar bias patterns. Termed BicaVis, our spatiotemporal bias pattern visual analytics system is proposed to assist experts in drafting calibration curves on the basis of these bias patterns. To verify the effectiveness of our approach, we conduct two case studies with real-world reanalysis datasets. The feedback collected from domain experts confirms the efficacy of our approach.

Many adversarial attacks have been proposed to investigate the security issues of deep neural networks. In the black-box setting, current model stealing attacks train a substitute model to counterfeit the functionality of the target model. However, the training requires querying the target model. Consequently, the query complexity remains high, and such attacks can be defended easily. This study aims to train a generalized substitute model called "Simulator", which can mimic the functionality of any unknown target model. To this end, we build the training data with the form of multiple tasks by collecting query sequences generated during the attacks of various existing networks. The learning process uses a mean square error-based knowledge-distillation loss in the meta-learning to minimize the difference between the Simulator and the sampled networks. The meta-gradients of this loss are then computed and accumulated from multiple tasks to update the Simulator and subsequently improve generalization. When attacking a target model that is unseen in training, the trained Simulator can accurately simulate its functionality using its limited feedback. As a result, a large fraction of queries can be transferred to the Simulator, thereby reducing query complexity. Results of the comprehensive experiments conducted using the CIFAR-10, CIFAR-100, and TinyImageNet datasets demonstrate that the proposed approach reduces query complexity by several orders of magnitude compared to the baseline method. The implementation source code is released online1.

One major problem in black-box adversarial attacks is the high query complexity in the hard-label attack setting, where only the top-1 predicted label is available. In this paper, we propose a novel geometric-based approach called Tangent Attack (TA), which identifies an optimal tangent point of a virtual hemisphere located on the decision boundary to reduce the distortion of the attack. Assuming the decision boundary is locally flat, we theoretically prove that the minimum $\ell_2$ distortion can be obtained by reaching the decision boundary along the tangent line passing through such tangent point in each iteration. To improve the robustness of our method, we further propose a generalized method which replaces the hemisphere with a semi-ellipsoid to adapt to curved decision boundaries. Our approach is free of pre-training. Extensive experiments conducted on the ImageNet and CIFAR-10 datasets demonstrate that our approach can consume only a small number of queries to achieve the low-magnitude distortion. The implementation source code is released online.

As an important method of handling potential uncertainties in numerical simulations, ensemble simulation has been widely applied in many disciplines. Visualization is a promising and powerful ensemble simulation analysis method. However, conventional visualization methods mainly aim at data simplification and highlighting important information based on domain expertise instead of providing a flexible data exploration and intervention mechanism. Trial-and-error procedures have to be repeatedly conducted by such approaches. To resolve this issue, we propose a new perspective of ensemble data analysis using the attribute variable dimension as the primary analysis dimension. Particularly, we propose a variable uncertainty calculation method based on variable spatial spreading. Based on this method, we design an interactive ensemble analysis framework that provides a flexible interactive exploration of the ensemble data. Particularly, the proposed spreading curve view, the region stability heat map view, and the temporal analysis view, together with the commonly used 2D map view, jointly support uncertainty distribution perception, region selection, and temporal analysis, as well as other analysis requirements. We verify our approach by analyzing a real-world ensemble simulation dataset. Feedback collected from domain experts confirms the efficacy of our framework.

We propose an interactive visual analytical approach to exploring and diagnosing the dynamic load balance (data and task partition) process of parallel particle tracing in flow visualization. To understand the complex nature of the parallel processes, it is necessary to integrate the information of the behaviors and patterns of the computing processes, data changes and movements, task status and exchanges, and gain the insight of the relationships among them. In our proposed approach, the data and task behaviors are visualized through a graph with a fine-designed layout, in which node glyphs are dedicated to showing the status of processes and the links represent the data or task transfer between different computation rounds and processes. User interactions are supported to facilitate the exploration of performance analysis. We provide a case study to demonstrate that the proposed approach enables users to identify the bottlenecks during this process, and thus help optimize the related algorithms.

The deficiency of labeled training data is one of the bottlenecks in 3D hand pose estimation from monocular RGB images. Synthetic datasets have a large number of images with precise annotations, but their obvious difference with real-world datasets limits the generalization ability. Few efforts have been made to bridge the gap between the two domains in terms of their large differences. In this paper, we propose a domain adaptation method called Adaptive Wasserstein Hourglass for weakly-supervised 3D hand pose estimation to close the large gap between synthetic and real-world datasets flexibly. Adaptive Wasserstein Hourglass utilizes a feature similarity metric to identify the differences and explore the common features (e.g., hand structure) of the two datasets. Common features are drawn close adaptively during the training, whereas domain-specific features retain the differences. Learning common features helps the network in focusing on pose-related information, whereas maintaining domain-specific features reduces the optimization difficulty when closing the big gap between two domains. Extensive evaluations on two benchmark datasets demonstrate that our method succeeds in distinguishing different features and achieves optimal results when compared with state-of-the-art 3D pose estimation approaches and domain adaptation methods.

An effective video classification method by means of a small number of samples is urgently needed. The deficiency of samples could be alleviated by generating samples through generative adversarial networks (GANs). However, the generation of videos in a typical category remains underexplored because the complex actions and the changeable viewpoints are difficult to simulate. Thus, applying GANs to perform video augmentation is difficult. In this study, we propose a generative data augmentation method for video classification using dynamic images. The dynamic image compresses the motion information of a video into a still image, removing the interference factors such as the background. Thus, utilizing the GANs to augment dynamic images can keep the categorical motion information and save memory compared with generating videos. To deal with the uneven quality of generated images, we propose a self-paced selection method to automatically select high-quality generated samples for training. These selected dynamic images are used to enhance the features, attain regularization, and finally achieve video augmentation. Our method is verified on two benchmark datasets, namely, HMDB51 and UCF101. Experimental results show that the method remarkably improves the accuracy of video classification under the circumstance of sample insufficiency and sample imbalance.

Abstract Despite the significance of tracking human mobility dynamics in a large‐scale earthquake evacuation for an effective first response and disaster relief, the general understanding of evacuation behaviors remains limited. Numerous individual movement trajectories, disaster damages of civil engineering, associated heterogeneous data attributes, as well as complex urban environment all obscure disaster evacuation analysis. Although visualization methods have demonstrated promising performance in emergency evacuation analysis, they cannot effectively identify and deliver the major features like speed or density, as well as the resulting evacuation events like congestion or turn‐back. In this study, we propose a shot design approach to generate customized and narrative animations to track different evacuation features with different exploration purposes of users. Particularly, an intuitive scene feature graph that identifies the most dominating evacuation events is first constructed based on user‐specific regions or their tracking purposes on a certain feature. An optimal camera route, i.e., a storyboard is then calculated based on the previous user‐specific regions or features. For different evacuation events along this route, we employ the corresponding shot design to reveal the underlying feature evolution and its correlation with the environment. Several case studies confirm the efficacy of our system. The feedback from experts and users with different backgrounds suggests that our approach indeed helps them better embrace a comprehensive understanding of the earthquake evacuation.

Deep neural networks (DNNs) are vulnerable to the adversarial attack which is maliciously implemented by adding human-imperceptible perturbation to images and thus leads to incorrect prediction. Existing studies have proposed various methods to detect the new adversarial attacks. However, new attack methods keep evolving constantly and yield new adversarial examples to bypass the existing detectors. It needs to collect tens of thousands samples to train detectors, while the new attacks evolve much more frequently than the high-cost data collection. Thus, this situation leads the newly evolved attack samples to remain in small scales. To solve such few-shot problem with the evolving attacks, we propose a meta-learning based robust detection method to detect new adversarial attacks with limited examples. Specifically, the learning consists of a double-network framework: a task-dedicated network and a master network which alternatively learn the detection capability for either seen attack or a new attack. To validate the effectiveness of our approach, we construct the benchmarks with few-shot-fashion protocols based on three conventional datasets, i.e. CIFAR-10, MNIST and Fashion-MNIST. Comprehensive experiments are conducted on them to verify the superiority of our approach with respect to the traditional adversarial attack detection methods. The implementation code is available online.

The use of scatterplots is an important method for multivariate data visualization. The point distribution on the scatterplot, along with variable values represented by each point, can help analyze underlying patterns in data. However, determining the multivariate data variation on a scatterplot generated using projection methods, such as multidimensional scaling, is difficult. Furthermore, the point distribution becomes unclear when the data scale is large and clutter problems occur. These conditions can significantly decrease the usability of scatterplots on multivariate data analysis. In this study, we present a cluster-based visual abstraction method to enhance the visualization of multivariate scatterplots. Our method leverages an adapted multilabel clustering method to provide abstractions of high quality for scatterplots. An image-based method is used to deal with large scale data problem. Furthermore, a suite of glyphs is designed to visualize the data at different levels of detail and support data exploration. The view coordination between the glyph-based visualization and the table lens can effectively enhance the multivariate data analysis. Through numerical evaluations for data abstraction quality, case studies and a user study, we demonstrate the effectiveness and usability of the proposed techniques for multivariate data analysis on scatterplots.

Predicting the gender of users in social media has aroused great interests in recent years. Almost all existing studies rely on the the content features extracted from the main texts like tweets or reviews. It is sometimes difficult to extract content information since many users do not write any posts at all. In this paper, we present a novel framework which uses only the users' ids and their social contexts for gender prediction. The key idea is to represent users in the embedding connection space. A user often has the social context of family members, schoolmates, colleagues, and friends. This is similar to a word and its contexts in documents, which motivates our study. However, when modifying the word embedding technique for user embedding, there are two major challenges. First, unlike the syntax in language, no rule is responsible for the composition of the social contexts. Second, new users were not seen when learning the representations and thus they do not have embedding vectors. Two strategies circular ordering and incremental updating are proposed to solve these problems. We evaluate our methodology on two real data sets. Experimental results demonstrate that our proposed approach is significantly better than the traditional graph representation and the state-of-the-art graph embedding baselines. It also outperforms the content based approaches by a large margin.

Video annotation is an effective way to facilitate content-based analysis for videos. Automatic machine learning methods are commonly used to accomplish this task. Among these, active learning is one of the most effective methods, especially when the training data cost a great deal to obtain. One of the most challenging problems in active learning is the sample selection. Various sampling strategies can be used, such as uncertainty, density, and diversity, but it is difficult to strike a balance among them. In this paper, we provide a visualization-based batch mode sampling method to handle such a problem. An iso-contour-based scatterplot is used to provide intuitive clues for the representativeness and informativeness of samples and assist users in sample selection. A semisupervised metric learning method is incorporated to help generate an effective scatterplot reflecting the high-level semantic similarity for visual sample selection. Moreover, both quantitative and qualitative evaluations are provided to show that the visualization-based method can effectively enhance sample selection in active learning.

Graph cut has proven to be an effective scheme to solve a wide variety of segmentation problems in vision and graphics community. The main limitation of conventional graph-cut implementations is that they can hardly handle large images or videos because of high computational complexity. Even though there are some parallelization solutions, they commonly suffer from the problems of low parallelism (on CPU) or low convergence speed (on GPU). In this paper, we present a novel graph-cut algorithm that leverages a parallelized jump flooding technique and an heuristic push-relabel scheme to enhance the graph-cut process, namely, back-and-forth relabel, convergence detection, and block-wise push-relabel. The entire process is parallelizable on GPU, and outperforms the existing GPU-based implementations in terms of global convergence, information propagation, and performance. We design an intuitive user interface for specifying interested regions in cases of occlusions when handling video sequences. Experiments on a variety of data sets, including images (up to 15 K × 10 K), videos (up to 2.5 K × 1.5 K × 50), and volumetric data, achieve high-quality results and a maximum 40-fold (139-fold) speedup over conventional GPU (CPU-)-based approaches.

As a novel type of real-time social networking service, microblogging has already become ubiquitous and an irreplaceable tool. Tracking in the pulse of retweeting propagation is important and meaningful. In this paper, we investigate how information propagation in a specific microblogging platform evolves to identify relevant patterns and understand dynamic attributes of information propagation and the underlying sociological motivations. More specifically, based on the node-link diagram, we propose three efficient strategies to map the multiple attributes of information propagation graph to appropriate visual elements. For revealing the dynamic attributes, we propose two models: the depth-varying and the time-varying parallel data model to illustrate the temporal evolution efficiently. We also present a novel method by combining the traditional scatter plot with Hough transformation to represent the distribution of propagation instances and trace the propagation speeds. We integrate our methods to a visual mining tool and develop several interactive features. We demonstrate how our approaches improve the understanding of the propagation graph from a visual perspective by employing propagation datasets collected from Sina Weibo, the largest microblogging service provider in mainland China. Meanwhile, this visual mining tool has been evaluated by data analysts and successfully used in Sina Corporation as a helpful assistant to them.

Color mapping plays a critical role in visualization of time-varying data and also sets a challenge for researchers due to the consistency of mapping and great changes in time-varying data. In order to solve this problem and generate feature-prominent animation, we present a two phase optimization technique using bilateral filtering and global energy functions. In the first phase, for each time step, we use a weighted mapping function which combines linear mapping and feature histogram. In the second phase, an optimization function taking global color mapping and minimum color difference into consideration is designed. So users can clearly distinguish between data in variable time steps and easily understand the corresponding relationships between different structures. The experiments' results show that our method can achieve high quality visualization for both static and time-varying data.

Parallel performance has been a challenging topic in streamline visualization for large unstructured flow datasets on parallel distributed-memory computers. It depends strongly on domain partitions. Unsuitable partitions often lead to severe load imbalance and high frequent communications among the domain partitions. To address the problem, we present an approach to flow data partitioning taking account of flow directions and features. Multilevel spectral graph bisection method is employed to reduce communication and synchronization overhead among distributed domains. Edge weights in the corresponding adjacent matrix is defined based on an anisotropic local diffusion operator which assigns strong coupling along flow direction and weak coupling orthogonal to flow. Meanwhile, the distributions of seed points and flow features such as vortex structure are also considered in partitioning so as to obtain good load balance. The experimental results are given to show the feasibility and effectiveness of our method.