Showing papers in "Computers & Graphics in 2021"

TL;DR: A novel method based on graph convolutional networks to tackle the problem of automatic dance generation from audio information using an adversarial learning scheme conditioned on the input music audios to create natural motions preserving the key movements of different music styles.

TL;DR: A comprehensive survey of LIDAR-based 3D object detection methods is presented wherein an analysis of existing methods is addressed by taking into account a new categorisation that relies upon a common operational pipeline which describes the end-to-end functionality of each method.

TL;DR: In this article, the authors presented a case study of creating and training a robot arm digital twin as an approach for AI training in a virtual space and applying this simulation learning within a physical space.

TL;DR: A collaborative virtual reality (VR) environment to assist liver surgeons in tumor surgery planning is presented to improve virtual resection planning between surgeons in a remote or co-located environment.

TL;DR: The field of single-view 3D shape reconstruction and generation using deep learning techniques has seen rapid growth in the past five years as mentioned in this paper, and a plethora of methods have been continuously proposed with the aim of pushing the state of research further.

TL;DR: The ARtention as discussed by the authors, a design space for gaze interaction specifically tailored for in-situ AR information interfaces, highlights three important dimensions to consider in the UI design of gaze-enabled applications: transitions from reality to the virtual interface, from single-to multi-layer content, and from information consumption to selection tasks.

TL;DR: A literature review shows that evaluation is frequently performed in ad-hoc manners, i.e., disregarding adapting the evaluation methods to collaborative AR, and suggests minimal support of existing frameworks and a lack of theories and guidelines to guide the characterization of the collaborative process using AR.

TL;DR: The results show that the handcrafted algorithm has balanced performance over all classes, while learning-based methods achieve overwhelming performance but suffer from the class-imbalanced problem and may fail on minority classes.

TL;DR: The result of the SHREC 2021: Track on Skeleton-based Hand Gesture Recognition in the Wild contest is presented, showing the performances of the techniques proposed by four research groups on the challenging task compared with a simple baseline method.

TL;DR: A multigranular model of co-adaptive visual analysis that is centered around incremental learning goals derived from a hierarchical taxonomy of learning goals from pedagogy, which captures how both actors adapt their data-, task-, and user/system-models over time.

TL;DR: It is demonstrated that changing visual perspective in VR is capable of eliciting inter- brain synchrony, demonstrating that VR could be an exciting platform to explore the phenomena of inter-brain synchrony further and provide a deeper understanding of the neuroscience of human communication.

TL;DR: Wang et al. as discussed by the authors proposed an inception-based deep network architecture called PIG-Net, which effectively characterizes the local and global geometric details of the point clouds.

TL;DR: A conceptual framework to support researchers in conducting evaluations in a more structured manner is outlined, and an evaluation toolkit is proposed to support contextual data collection and analysis in remote collaboration scenarios and obtain an additional perspective on selected dimensions of collaboration.

TL;DR: A novel Augmented Virtuality (AV) interface that enables people to naturally interact with a mobile phone in real time in a virtual environment and enables the user to operate a virtual mobile phone aligned with their real phone.

TL;DR: A novel framework for skeleton-based dynamic hand gesture recognition and a compact joints encoding method that can adaptively select compact joints based on the convex hull of the hand skeleton and encode them into a skeleton image for fully extracting spatial features are proposed.

TL;DR: In this article, the authors investigated the impact of facial anthropomorphism on the sense of body ownership, avatar attractiveness, social presence and performance in two collaborative tasks, and found that the more attractive the avatar, the shorter the completion duration of the game.

TL;DR: Observations show that immersive 3D sketching is a unique form of visual representation that facilitates the rapid and flexible creation of large and detailed 3D computer models.

TL;DR: It is demonstrated how the provided explanatory views can be combined to augment each other’s value and thereby lead to refined insights in the data for several high-dimensional datasets, and how these insights correlate with known facts about the data under study.

TL;DR: In this paper, a systematic review of technological multisensory applications in cultural heritage is presented, focusing on technologies used, purpose of the experience, stimuli explored, evaluation process, main findings obtained, and limitations found.

TL;DR: In this article, an immersive analytics system with effective visualization and interaction techniques is introduced to enable architects to assess designs in a virtual reality (VR) environment, which includes a customized parallel coordinates plot (PCP) design to facilitate quantitative assessment of high-dimensional design metrics.

TL;DR: Investigating the potential applications of immersive technology and advantages and potential drawbacks that should be considered when integrating the technology into the workplace leads to the conclusion that immersive technology is the step to the future in terms of smart product development strategies to implement for employers.

TL;DR: This work exposes how AR can help users to have better performances in a decision-making context, particularly in EMC related tasks, while also furthering the research in the ASV field.

TL;DR: The results show a predominance of learning methods on image-based multi-view representations to characterize 3D objects, and the problem presented in the challenges is far from being solved.

TL;DR: It is shown that evolutionary search can automatically optimize the encoder-decoder structure and meta-parameters of the DIP network, which serves as a content-specific prior to regularize these single image restoration tasks.

TL;DR: In this paper, a Pareto-optimality criterion based on the total support volume and the secluded support volume is defined as the support volume that is not accessible by a given set of machining tools.

TL;DR: A Principal Component Analysis (PCA)-based generative model describes the predicted spatial probability distributions of the incoming patient’s organs in the upcoming weeks of treatment, based on observations of past patients.

TL;DR: The proposed Beauty3DFaceNet is the first deep convolutional neural network to predict attractiveness on 3D faces with both geometry and texture information, and it validates that a deep learning network can effectively learn and predict 3D facial attractiveness.

TL;DR: Deep Radiance Caching (DRC) as discussed by the authors employs a denoising neural network with radiocaching to support a wide range of material types, without the requirement of offline pre-computation or training for each scene.

TL;DR: Experiments demonstrate that the proposed Multi-View Stereo network can generate results comparable with the state-of-the-art learning-based methods while reconstructing more geometric details and consuming less GPU memory.

TL;DR: The invariant descriptors provide an embedding into a fixed-dimensional feature space that can be used for various applications, e.g., as input features for deep and shallow learning techniques or as input for dimension reduction schemes to provide a visual reference for clustering shape collections.