Inverse Kinematics (IK) provides control over animation, facilitating the creation of full-body poses by utilizing target end-effector locations. Many approaches address the physical aspects of arranging limb configurations; however, systems that consider the psychological aspects of human motion are lacking. To this end, we introduce a quantitative translation of the qualitative concepts of Laban Movement Analysis (LMA) into computable, continuous style descriptors. Building upon this formulation, we also propose a data-driven Inverse Kinematics (IK) method that directly utilizes these LMA parameters to refine generated animations. Specifically, we refer to LMA Shape Qualities and the attitude towards the Kinesphere to control the orientation of the generated pose along the vertical and horizontal axes. Our Interpolator upsamples sparse end-effector keyframes into dense paths and modulates Time Effort at the trajectory level. Flow Effort is controlled by a pose-similarity objective that deliberately reduces pose similarity to the dataset examples. Through a perception user study, we show that the system can successfully apply LMA-based changes to the motion to express different personality traits. This data-driven system can ease the process of controlling the psychological aspect of generative animation.

This work investigates the effects of personality expression and embodiment in conversational agents. We extend a personality-driven conversational agent framework by integrating LLM-based conversation support to provide information about contemporary scientific topics. We describe a user study built on this system to evaluate two opposing personality styles using three models: a dialogue-only model that conveys personality verbally, an animated human model that expresses personality only through dialogue, and an animated human model expressing personality through dialogue and expressive animations. The users perceive all models positively regarding personality and learning outcomes; however, models with high personality traits are perceived as more engaging than those with low personality traits. We provide an analysis of personality perception, learning, and user experience.

ABSTRACT Large Language Models (LLMs) offer almost immediate human‐like quality responses to user queries. Conversational agent systems support natural language dialogues utilizing LLM backends in combination with Text‐to‐Speech (TTS) and Automatic Speech Recognition (ASR) technologies, enabling life‐like characters in virtual environments. This study investigates the relationship between user personality and perceived agent personality in LLM‐based natural language dialogue. We adopt a Virtual Reality (VR) setting where the user can talk with the agent that assumes the role of Socrates, the famous philosopher. To this end, we utilize a three‐dimensional (3D) avatar model resembling Socrates and use specific LLM prompts to get stylistic answers from OpenAI's Chat Completions Application Programming Interface (API). Our user study measures the agent's personality and the system's ease of use, quality, realism, and immersion concerning the user's self‐reported personality. The results suggest that the user's conscientiousness, extraversion, and emotional stability have a moderate effect on certain personality factors and system qualities. User conscientiousness affects the perceived ease of use, quality, and realism, while user extraversion affects perceived agent conscientiousness, system realism, and immersion. Additionally, the user's emotional stability correlates with perceived extraversion and agreeableness.

We express our personality through verbal and nonverbal behavior. While verbal cues are mostly related to the semantics of what we say, nonverbal cues include our posture, gestures, and facial expressions. Appropriate expression of these behavioral elements improves conversational virtual agents’ communication capabilities and realism. Although previous studies focus on co-speech gesture generation, they do not consider the personality aspect of the synthesized animations. We show that automatically generated co-speech gestures naturally express personality traits, and heuristics-based adjustments for such animations can further improve personality expression. To this end, we present a framework for enhancing co-speech gestures with the different personalities of the Five-Factor model. Our experiments suggest that users perceive increased realism and improved personality expression when combining heuristics-based motion adjustments with co-speech gestures.

Interactively visualizing large finite element simulation data on High-Performance Computing (HPC) systems poses several difficulties. Some of these relate to unstructured data, which, even on a single node, is much more expensive to render compared to structured volume data. Worse yet, in the data parallel rendering context, such data with highly non-convex spatial domain boundaries will cause rays along its silhouette to enter and leave a given rank's domains at different distances. This straddling, in turn, poses challenges for both ray marching, which usually assumes successive elements to share a face, and compositing, which usually assumes a single fragment per pixel per rank. We holistically address these issues using a combination of three inter-operating techniques: first, we use a highly optimized GPU ray marching technique that, given an entry point, can march a ray to its exit point with high-performance by exploiting an exclusive-or (XOR) based compaction scheme. Second, we use hardware-accelerated ray tracing to efficiently find the proper entry points for these marching operations. Third, we use a "deep" compositing scheme to properly handle cases where different ranks' ray segments interleave in depth. We use GPU-to-GPU remote direct memory access (RDMA) to achieve interactive frame rates of 10-15 frames per second and higher for our motivating use case, the Fun3D NASA Mars Lander.

Abstract Point cloud registration is a fundamental problem in computer vision. The problem encompasses critical tasks such as feature estimation, correspondence matching, and transformation estimation. The point cloud registration problem can be cast as a quantile matching problem. We refined the quantile assignment algorithm by integrating prevalent feature descriptors and transformation estimation methods to enhance the correspondence between the source and target point clouds. We evaluated the performances of these descriptors and methods with our approach through controlled experiments on a dataset we constructed using well-known 3D models. This systematic investigation led us to identify the most suitable methods for complementing our approach. Subsequently, we devised a new end-to-end, coarse-to-fine pairwise point cloud registration framework. Finally, we tested our framework on indoor and outdoor benchmark datasets and compared our results with state-of-the-art point cloud registration methods.

Estimating 3D human texture from a single image is essential in graphics and vision. It requires learning a mapping function from input images of humans with diverse poses into the parametric (uv) space and reasonably hallucinating invisible parts. To achieve a high-quality 3D human texture estimation, we propose a framework that adaptively samples the input by a deformable convolution where offsets are learned via a deep neural network. Additionally, we describe a novel cycle consistency loss that improves view generalization. We further propose to train our framework with an uncertainty-based pixel-level image reconstruction loss, which enhances color fidelity. We compare our method against the state-of-the-art approaches and show significant qualitative and quantitative improvements.

Abstract Volume data these days is usually massive in terms of its topology, multiple fields, or temporal component. With the gap between compute and memory performance widening, the memory subsystem becomes the primary bottleneck for scientific volume visualization. Simple, structured, regular representations are often infeasible because the buses and interconnects involved need to accommodate the data required for interactive rendering. In this state‐of‐the‐art report, we review works focusing on large‐scale volume rendering beyond those typical structured and regular grid representations. We focus primarily on hierarchical and adaptive mesh refinement representations, unstructured meshes, and compressed representations that gained recent popularity. We review works that approach this kind of data using strategies such as out‐of‐core rendering, massive parallelism, and other strategies to cope with the sheer size of the ever‐increasing volume of data produced by today's supercomputers and acquisition devices. We emphasize the data management side of large‐scale volume rendering systems and also include a review of tools that support the various volume data types discussed.

Abstract The movement style is an adequate descriptor of different personalities. While many studies investigate the relationship between apparent personality and high‐level motion qualities in humans, similar research for animal characters still needs to be done. The variety in animals' skeletal configurations and texture complicates their pose estimation process. Our affect analysis framework includes a workflow for pose extraction in animal characters and a parameterization of the high‐level animal motion descriptors inspired by Laban movement analysis. Using a data set of quadruped walk cycles, we prove the display of typologies in cartoon animal characters, reporting the point‐biserial correlation between our motion parameters and the Sasang categories that reflect different personalities.

We propose a simple yet effective method for clustering finite elements to improve preprocessing times and rendering performance of unstructured volumetric grids without requiring auxiliary connectivity data. Rather than building bounding volume hierarchies (BVHs) over individual elements, we sort elements along with a Hilbert curve and aggregate neighboring elements together, improving BVH memory consumption by over an order of magnitude. Then to further reduce memory consumption, we cluster the mesh on the fly into sub-meshes with smaller indices using a series of efficient parallel mesh re-indexing operations. These clusters are then passed to a highly optimized ray tracing API for point containment queries and ray-cluster intersection testing. Each cluster is assigned a maximum extinction value for adaptive sampling, which we rasterize into non-overlapping view-aligned bins allocated along the ray. These maximum extinction bins are then used to guide the placement of samples along the ray during visualization, reducing the number of samples required by multiple orders of magnitude (depending on the dataset), thereby improving overall visualization interactivity. Using our approach, we improve rendering performance over a competitive baseline on the NASA Mars Lander dataset from 6× (1 frame per second (fps) and 1.0 M rays per second (rps) up to now 6 fps and 12.4 M rps, now including volumetric shadows) while simultaneously reducing memory consumption by 3×(33 GB down to 11 GB) and avoiding any offline preprocessing steps, enabling high-quality interactive visualization on consumer graphics cards. Then by utilizing the full 48 GB of an RTX 8000, we improve the performance of Lander by 17 × (1 fps up to 17 fps, 1.0 M rps up to 35.6 M rps).

MOTIVATION: Genome data is a subject of study for both biology and computer science since the start of the Human Genome Project in 1990. Since then, genome sequencing for medical and social purposes becomes more and more available and affordable. Genome data can be shared on public websites or with service providers (SPs). However, this sharing compromises the privacy of donors even under partial sharing conditions. We mainly focus on the liability aspect ensued by the unauthorized sharing of these genome data. One of the techniques to address the liability issues in data sharing is the watermarking mechanism. RESULTS: To detect malicious correspondents and SPs-whose aim is to share genome data without individuals' consent and undetected-, we propose a novel watermarking method on sequential genome data using belief propagation algorithm. In our method, we have two criteria to satisfy. (i) Embedding robust watermarks so that the malicious adversaries cannot temper the watermark by modification and are identified with high probability. (ii) Achieving ϵ-local differential privacy in all data sharings with SPs. For the preservation of system robustness against single SP and collusion attacks, we consider publicly available genomic information like Minor Allele Frequency, Linkage Disequilibrium, Phenotype Information and Familial Information. Our proposed scheme achieves 100% detection rate against the single SP attacks with only 3% watermark length. For the worst case scenario of collusion attacks (50% of SPs are malicious), 80% detection is achieved with 5% watermark length and 90% detection is achieved with 10% watermark length. For all cases, the impact of ϵ on precision remained negligible and high privacy is ensured. AVAILABILITY AND IMPLEMENTATION: https://github.com/acoksuz/PPRW\_SGD\_BPLDP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Abstract We describe a hybrid acceleration structure for ray tracing. The hybrid structure is a Bounding Volume Hierarchy (BVH) where the leaf nodes are tetrahedralized for a decent ray‐surface intersection performance. We use the hybrid acceleration structure (BTH) in a two‐level acceleration structure for rendering animated scenes. There is a BVH at the top level in this two‐level structure and the proposed hybrid structure (BTH) at the bottom level. We test the proposed two‐level structure (BVH‐BTH) for various animated scenes and obtained promising results against other acceleration structures in terms of rendering times. The two‐level BVH‐BTH structure outperforms the two‐level BVH structure for the tested dynamic scenes.

Indoor positioning is one of the difficult problems in current navigation systems. There is an increasing demand for detecting the locations of objects and humans inside closed environments in various fields including surveillance, robotics, and entertainment. Recent works focus on indoor navigation systems using different technologies including Wireless Local Area Network (WLAN), Radio Frequency Identification (RFID), Inertial Measurement Unit (IMU), and Simultaneous Localization and Mapping (SLAM). Research reveals using these technologies alone is inefficient in terms of accuracy and cost. To address this issue, we propose a marker-based Augmented Reality (AR) indoor navigation system with integrated SLAM and IMU. We use Unity's AR Foundation Framework for highly accurate results with minimum hardware requirements.

Early detection of wildfire smoke in real-time is essentially important in forest surveillance and monitoring systems. We propose a vision-based method to detect smoke using Deep Convolutional Generative Adversarial Neural Networks (DC-GANs). Many existing supervised learning approaches using convolutional neural networks require substantial amount of labeled data. In order to have a robust representation of sequences with and without smoke, we propose a two-stage training of a DCGAN. Our training framework includes, the regular training of a DCGAN with real images and noise vectors, and training the discriminator separately using the smoke images without the generator. Before training the networks, the temporal evolution of smoke is also integrated with a motion-based transformation of images as a pre-processing step. Experimental results show that the proposed method effectively detects the smoke images with negligible false positive rates in real-time.

Augmentation of virtual agents in real crowd videos is an important task for different applications from design simulations of social environments to modeling abnormalities in crowd behavior. We propose a framework for this task, namely for augmenting virtual agents in real crowd videos. Our framework utilizes homography-based video stabilization, Dalal-Triggs detector [1] for pedestrian detection and state-based tracking algorithms to automatically locate the pedestrians in video frames and project them into our 3D simulated environment, where the navigable area of the simulated environment is available as a manually designed and located navigation mesh. We represent the real pedestrians in the video as simple three-dimensional (3D) models in our simulation environment. 3D models representing real, projected agents and the augmented virtual agents are simulated using local path planning coupled with a collision detection and avoidance algorithm, called Reciprocal Velocity Obstacles (RVO) [2]. The virtual agents augmented into the video move plausibly without colliding with static and dynamic obstacles, including other virtual agents and real pedestrians. We provide an extensive graphical user interface for controlling the virtual agents in the scene, including collision avoidance parameters, adjusting the camera in the scene and some standard video player options.

Abstract Predicting interest points of virtual characters and accurately simulating their gaze behavior play a significant role for realistic crowd simulations. We propose a saliency model that enables virtual agents to produce plausible gaze behavior. The model measures the effects of distinct saliency features implemented by examining the state‐of‐the‐art perception studies. When predicting an agent's interest point, we compute the saliency scores by using a weighted sum function for other agents and environment objects in the field of view of the agent for each frame. Then, we determine the most salient entity for each agent in the scene; thus, agents gain a visual understanding of their environment. Besides, our model introduces new aspects to crowd perception, such as perceiving characters as groups of people and applying social norms on crowd gaze behavior, effects of agent personality on gaze, gaze copy phenomena, and effects of agent velocity on attention. For evaluation, we compare the resulting saliency gaze model with real‐world crowd behavior in captured videos. In the experiments, we simulate the gaze behavior in real crowds. The results show that the proposed approach generates plausible gaze behaviors and is easily adaptable to varying scenarios for virtual crowds.

In the social psychology literature, crowds are classified as audiences and mobs. Audiences are passive crowds, whereas mobs are active crowds with emotional, irrational and seemingly homogeneous behavior. In this study, we aim to create a system that enables the specification of different crowd types ranging from audiences to mobs. In order to achieve this goal we parametrize the common properties of mobs to create collective misbehavior. Because mobs are characterized by emotionality, we describe a framework that associates psychological components with individual agents comprising a crowd and yields emergent behaviors in the crowd as a whole. To explore the effectiveness of our framework we demonstrate two scenarios simulating the behavior of distinct mob types.

As a result of increasing communication demands, application-specific and scalable Network-on-Chips (NoCs) have emerged to connect processing cores and subsystems in Multiprocessor System-on-Chips. A challenge in application-specific NoC design is to find the right balance among different tradeoffs, such as communication latency, power consumption and chip area. We propose a novel approach that generates latency-aware heterogeneous NoC topology. Experimental results show that our approach improves the total communication latency up to 27% with modest power consumption.

Terrain rendering is a crucial part of many real-time applications. The easiest way to process and visualize terrain data in real time is to constrain the terrain model in several ways. This decreases the amount of data to be processed and the amount of processing power needed, but at the cost of expressivity and the ability to create complex terrains. The most popular terrain representation is a regular 2D grid, where the vertices are displaced in a third dimension by a displacement map, called a heightmap. This is the simplest way to represent terrain, and although it allows fast processing, it cannot model terrains with volumetric features. Volumetric approaches sample the 3D space by subdividing it into a 3D grid and represent the terrain as occupied voxels. They can represent volumetric features but they require computationally intensive algorithms for rendering, and their memory requirements are high. We propose a novel representation that combines the voxel and heightmap approaches, and is expressive enough to allow creating terrains with caves, overhangs, cliffs, and arches, and efficient enough to allow terrain editing, deformations, and rendering in real time.

In any practical application of the 2-D-to-3-D conversion that involves storage and transmission, representation efficiency has an undisputable importance that is not reflected in the attention the topic received. In order to address this problem, a novel algorithm, which yields efficient 3-D representations in the rate distortion sense, is proposed. The algorithm utilizes two views of a scene to build a mesh-based representation incrementally, via adding new vertices, while minimizing a distortion measure. The experimental results indicate that, in scenes that can be approximated by planes, the proposed algorithm is superior to the dense depth map and, in some practical situations, to the block motion vector-based representations in the rate-distortion sense.

We describe a method to automatically extract important video objects for object-based indexing. Most of the existing salient object detection approaches detect visually conspicuous structures in images, while our method aims to find regions that may be important for indexing in a video database system. Our method works on a shot basis. We first segment each frame to obtain homogeneous regions in terms of color and texture. Then, we extract a set of regional and inter-regional color, shape, texture and motion features for all regions, which are classified as being important or not using SVMs trained on a few hundreds of example regions. Finally, each important region is tracked within each shot for trajectory generation and consistency check. Experimental results from news video sequences show that the proposed approach is effective.

This paper proposes a novel 3D piecewise planar reconstruction algorithm, to build a 3D scene representation that minimizes the intensity error between a particular frame and its prediction. 3D scene geometry is exploited to remove the visual redundancy between frame pairs for any predictive coding scheme. This approach associates the rate increase with the quality of representation, and is shown to be rate-distortion efficient by the experiments.

In this paper, a 3D graphics environment for virtual garment design and simulation is presented. The proposed system enables the three dimensional construction of a garment from its cloth panels, for which the underlying structure is a mass-spring model. The garment construction process is performed through automatic pattern generation, posterior correction, and seaming. Afterwards, it is possible to do fitting on virtual mannequins as if in a real life tailor's workshop. The system provides the users with the flexibility to design their own garment patterns and make changes on the garment even after the dressing of the model. Furthermore, rendering alternatives for the visualization of knitted and woven fabric are presented.

3-D scene representation is utilized during scene extraction, modeling, transmission and display stages of a 3DTV framework. To this end, different representation technologies are proposed to fulfill the requirements of 3DTV paradigm. Dense point-based methods are appropriate for free-view 3DTV applications, since they can generate novel views easily. As surface representations, polygonal meshes are quite popular due to their generality and current hardware support. Unfortunately, there is no inherent smoothness in their description and the resulting renderings may contain unrealistic artifacts. NURBS surfaces have embedded smoothness and efficient tools for editing and animation, but they are more suitable for synthetic content. Smooth subdivision surfaces, which offer a good compromise between polygonal meshes and NURBS surfaces, require sophisticated geometry modeling tools and are usually difficult to obtain. One recent trend in surface representation is point-based modeling which can meet most of the requirements of 3DTV, however the relevant state-of-the-art is not yet mature enough. On the other hand, volumetric representations encapsulate neighborhood information that is useful for the reconstruction of surfaces with their parallel implementations for multiview stereo algorithms. Apart from the representation of 3-D structure by different primitives, texturing of scenes is also essential for a realistic scene rendering. Image-based rendering techniques directly render novel views of a scene from the acquired images, since they do not require any explicit geometry or texture representation. 3-D human face and body modeling facilitate the realistic animation and rendering of human figures that is quite crucial for 3DTV that might demand real-time animation of human bodies. Physically based modeling and animation techniques produce impressive results, thus have potential for use in a 3DTV framework for modeling and animating dynamic scenes. As a concluding remark, it can be argued that 3-D scene and texture representation techniques are mature enough to serve and fulfill the requirements of 3-D extraction, transmission and display sides in a 3DTV scenario.

A framework for realistic rendering of a multi-layered human body model is proposed in this paper. The human model is composed of three layers: skeleton, muscle, and skin. The skeleton layer, represented by a set of joints and bones, controls the animation of the human body using inverse kinematics. Muscles are represented with action lines that are defined by a set of control points. An action line applies the force produced by a muscle on the bones and on the skin mesh. The skin layer is modeled as a 3D mesh and deformed during animation by binding the skin layer to both the skeleton and muscle layers. The skin is deformed by a two-step algorithm according to the current state of the skeleton and muscle layers. Performance experiments show that it is possible to obtain real-time frame rates for a moderately complex human model containing approximately 33,000 triangles on the skin layer.

The paper proposes a novel method to detect fire and/or flame by processing the video data generated by an ordinary camera monitoring a scene. In addition to ordinary motion and color clues, flame and fire flicker are detected by analyzing the video in the wavelet domain. Periodic behavior in flame boundaries is detected by performing a temporal wavelet transform. Color variations in fire are detected by computing the spatial wavelet transform of moving fire-colored regions. Other clues used in the fire detection algorithm include irregularity of the boundary of the fire-colored region and the growth of such regions in time. All of the above clues are combined to reach a final decision.

We present a computer vision based text and equation editor for LATEX. The user writes text and equations on paper and a camera attached to a computer records the actions of the user. In particular, positions of the pen-tip in consecutive image frames are detected. Next, directional and positional information about characters are calculated using these positions. Then, this information is used for on-line character classification. After characters and symbols are found, the corresponding LATEX code is generated.

There is an accelerating demand to access the visual content of documents stored in historical and cultural archives. Availability of electronic imaging tools and effective image processing techniques makes it feasible to process the multimedia data in large databases. In this paper, a framework for content-based retrieval of historical documents in the Ottoman Empire archives is presented. The documents are stored as textual images, which are compressed by constructing a library of symbols occurring in a document, and the symbols in the original image are then replaced with pointers into the codebook to obtain a compressed representation of the image. The features in wavelet and spatial domain based on angular and distance span of shapes are used to extract the symbols. In order to make content-based retrieval in historical archives, a query is specified as a rectangular region in an input image and the same symbol-extraction process is applied to the query region. The queries are processed on the codebook of documents and the query images are identified in the resulting documents using the pointers in textual images. The querying process does not require decompression of images. The new content-based retrieval framework is also applicable to many other document archives using different scripts.

Visualization of large geometric environments has always been an important problem of computer graphics. We present a framework for the stereoscopic view-dependent visualization of large scale terrain models. We use a quadtree based multiresolution representation for the terrain data. This structure is queried to obtain the view-dependent approximations of the terrain model at different levels of detail. In order not to lose depth information, which is crucial for the stereoscopic visualization, we make use of a different simplification criterion, namely, distance-based angular error threshold. We also present an algorithm for the construction of stereo pairs in order to speed up the view-dependent stereoscopic visualization. The approach we use is the simultaneous generation of the triangles for two stereo images using a single draw-list so that the view frustum culling and vertex activation is done only once for each frame. The cracking problem is solved using the dependency information stored for each vertex. We eliminate the popping artifacts that can occur while switching between different resolutions of the data using morphing. We implemented the proposed algorithms on personal computers and graphics workstations. Performance experiments show that the second eye image can be produced approximately 45 percent faster than drawing the two images separately and a smooth stereoscopic visualization can be achieved at interactive frame rates using continuous multiresolution representation of height fields.

We combined physically based modeling and parameterization to generate realistic speech animation on synthetic faces. We used physically based modeling for muscles. Muscles are modeled as forces deforming the mesh of polygons. A parameterization technique is used for generating mouth shapes for speech animation. Each meaningful part of a text, which is a letter in our case, corresponds to a specific mouth shape and the mouth shape is generated by setting a set of parameters used for representing the muscles and jaw rotation. We also developed a mechanism to generate and synchronize facial expressions while speaking. Some tags specifying the facial expressions are inserted into the input text together with the degree of the expression. In this way, the facial expression with the specified degree is generated and synchronized with speech animation.

Continuous deformable models are generally represented using a grid of control points. The elastic properties are then modeled using the interactions between these points. The formulations based on elasticity theory express these interactions using stiffness matrices. These matrices store the elastic properties of the models and they should be evolved in time according to changing elastic properties of the models. However, forming the stiffness matrices at any step of an animation is very difficult and sometimes the differential equations that should be solved to produce animation become ill-conditioned. Instead of modeling the elasticities using stiffness matrices, the interactions between model points could be expressed in terms of external spring forces. In this paper, a spring force formulation for animating elastically deformable models is presented. In this formulation, elastic properties of the materials are represented as external spring forces as opposed to forming complicated stiffness matrices. (C) 1997 Elsevier Science Ltd.

Physically-based modeling remedies the problem of producing realistic animation by including forces, masses, strain energies, and other physical quantities. The behavior of physically-based models is governed by the laws of rigid and nonrigid dynamics expressed through a set of equations of motion. This paper discusses various formulations for animating deformable models. The formulations based on elasticity theory express the interactions between discrete deformable model points using the stiffness matrices. These matrices store the elastic properties of the models and they should be evolved in time according to changing elastic properties of the models. An alternative to these formulations seems to be external force formulations of different types. In these types of formulations, elastic properties of the materials are represented as external spring or other tensile forces as opposed to forming complicated stiffness matrices.>