IEEE transactions on visualization and computer graphics最新文献

Understanding how individuals interpret charts is a crucial concern for visual data communication. This imperative has motivated a number of studies, including past work demonstrating that causal priors-a priori belief about causal relationships between concepts-can have significant influences on the perceived strength of variable relationships inferred from visualizations. This paper builds on these previous results, demonstrating that causal priors can also influence the types of patterns that people perceive as the most salient within ambiguous scatterplots that have roughly equal evidence for trend and cluster patterns. Using a mixed-design approach that combines a largescale online experiment for breadth of findings with an in-person think-aloud study for analytical depth, we investigated how users' interpretations are influenced by the interplay between causal priors and the visualized data patterns. Our analysis suggests two archetypal reasoning behaviors through which people often make their observations: contextualization, in which users accept a visual pattern that aligns with causal priors and use their existing knowledge to enrich interpretation, and rationalization, in which users encounter a pattern that conflicts with causal priors and attempt to explain away the discrepancy by invoking external factors, such as positing confounding variables or data selection bias. These findings provide initial evidence highlighting the critical role of causal priors in shaping high-level visualization comprehension, and introduce a vocabulary for describing how users reason about data that either confirms or challenges prior beliefs of causality.

The generation of anchor-style product promotion videos presents promising opportunities in e-commerce, advertising, and consumer engagement. Despite advancements in pose-guided human video generation, creating product promotion videos remains challenging. In addressing this challenge, we identify the integration of human-object interactions (HOI) into pose-guided human video generation as a core issue. To this end, we introduce AnchorCrafter, a novel diffusion-based system designed to generate 2D videos featuring a target human and a customized object, achieving high visual fidelity and controllable interactions. Specifically, we propose two key innovations: the HOI-appearance perception, which enhances object appearance recognition from arbitrary multi-view perspectives and disentangles object and human appearance, and the HOI-motion injection, which enables complex human-object interactions by overcoming challenges in object trajectory conditioning and inter-occlusion management. Extensive experiments show that our system improves object appearance preservation by 7.5%, and achieves the best video quality compared to existing state-of-the-art approaches. It also outperforms existing approaches in maintaining human motion consistency and high-quality video generation. Project page including data, code, and Huggingface demo: https://github.com/cangcz/AnchorCrafter.

Estimating the 6-DoF posture of parts in assembly-based modeling is a critical task in the fields of computer graphics, computer vision and robotics. A typical scenario involves enabling a machine agent to automatically assemble IKEA furniture using the provided parts. This paper presents HiFormer, a novel Hierarchical Transformer with Box-packed Positional Encoding, designed for highly automatic 3D part assembly. Our method addresses three important issues commonly encountered in 3D part assembly: 1) How to mitigate the overfitting problem associated with Transformer-based feature learning for 3D point clouds? 2) How to effectively model the relationships between the intragroup and intergroup parts? 3) How to compute positional encoding and integrate it into the Transformer for parts with diverse geometric forms in the coarse-to-fine assembly process? These challenges are tackled through three key contributions: 1) a multi-task 3D Swin Transformer with a two-stage training strategy for feature extraction, 2) a novel hierarchical Transformer for capturing part relationships at flattening, intragroup, and intergroup levels, and 3) an innovative box-packed positional encoding that enhances the Transformer by incorporating query, key, and value information derived from relative box positions. On the PartNet benchmark, our method outperforms the state-of-the-art PWH-MP model on three representative categories-Chair, Table, and Lamp-, achieving average improvements of 2.84% in Part Accuracy (PA) and 3.72% in Connection Accuracy (CA) for diversity modeling (with noise), and 3.55% in PA and 3.21% in CA for deterministic modeling (without noise).

This paper presents an interactive analysis framework for exploring data from photoelastic disk experiments, which serve as a model for two-dimensional granular materials. Granular materials, composed of discrete particles such as sand or gravel, exhibit behaviors resembling fluid or solid states depending on the system configuration. These behaviors arise from interparticle contact forces, which form complex force networks that govern the material's macroscopic behavior. Our framework is specifically designed to analyze such 2D ensembles of dynamic force networks, enabling the identification and characterization of their underlying structures. The framework is built around a topology-based, multiscale data segmentation in terms of force chains and cycles. The analysis methods are structured across three levels: (1) multiscale analysis of individual instances under specific loading conditions, (2) detailed exploration of single experiments encompassing a series of loading and unloading cycles, and (3) comparative analysis across experiments conducted under similar and differing setups. We demonstrate the capabilities of our framework with a case study for each of these levels.

This paper presents a novel approach for generating high-quality, cross-category 3D models from free-hand sketches with limited training data. We propose the first semi-supervised learning method to our knowledge for sketch-to-3D model conversion. Innovatively, we design a coarse-to-fine pipeline to perform the semi-supervised learning in the coarse stage and train a diffusion-based refiner to get a high-resolution 3D model. We designed a sketch-augmentation method for semi-supervised learning and integrated priors such as CLIP loss, shape prototypes, and adversarial loss to help generate high-quality results even with abstract and imprecise sketches. We also introduce an innovative procedural 3D generation method based on CAD code, which helps pre-train part of the network before fine-tuning with limited real data. Our approach, coupled with a specifically designed curriculum learning, allows us to generate high-quality 3D models across multiple categories with as few as 300 sketch-3D model pairs, marking a significant advancement over previous single-category approaches. In addition, we introduce the KO2D dataset, the largest collection of hand-drawn sketch-3D pairs to support further research in this area. As sketches are a far more intuitive and detailed way for users to express their unique ideas, we believe that this paper can move us closer to democratizing 3D content creation, enabling anyone to transform their ideas into 3D models effortlessly.

Dendroid stony corals build highly complex colonies that develop by asexual reproduction from a single coral polyp sitting in a cup-like exoskeleton, called corallite, resulting in a tree-like branching pattern of its exoskeleton. Despite their beauty and ecological importance as reef builders in tropical shallow-water and in huge cold-water coral mounds in the deep ocean, systematic studies investigating the ontogenetic morphological development of such coral colonies are largely missing. The main reasons for this lack of study are the large number of corallites, and the existence of many secondary joints/coenosteal bridges in the ideally tree-like structure that make a reconstruction of the skeleton tree extremely tedious. Herein, we present CoDA, the Coral Dendroid structure Analyzer, a visual analytics toolkit that allows for the first time to systematically create skeleton trees representing the correct biological relationship of even very complex dendroid stony corals and to perform ontogenetic morphological analyses based on it. Starting with an initial instance segmentation of the calices/corallites, CoDA estimates the skeleton tree and provides convenient tools and visualizations for proofreading and correcting segmentation and skeleton tree. Part of CoDA is CoDA.Graph, a feature-rich link-and-brush user interface for showing the extracted morphological features and graph layouts of the skeleton tree, enabling real-time exploration of complex coral colonies and their building blocks, the individual corallites and branches. The use of CoDA is exemplified on multiple specimens of the three most important reef-building cold-water coral species with largely varying morphotypes.

Redirected walking (RDW) subtly adjusts the user's visual perspective on head-mounted displays during natural walking to reduce forced resets, thus enlarging the size of the virtual environment that can be explored beyond that of the physical environment. Alignment-based RDW controllers aim to minimize spatial discrepancies by optimizing the alignment between the user's physical and virtual environments. We introduce a novel alignment-based method that dynamically calculates mapping functions between physical and virtual geometries to enhance the algorithm's awareness of the RDW environments. To achieve this, we first construct an abstract model defining a mapping function between physical and virtual geometries and establish feasibility constraints in differential form. We then concretize this mapping, optimize it, and develop a practical implementation for dynamic geometric mapping in RDW. Our approach distinguishes itself by determining dense spatial mappings around the user, rather than aligning environments according to limited metrics. Through extensive testing, our algorithm has proven to markedly decrease reset incidents in natural walking, surpassing existing RDW controllers. The introduction of dynamic geometric mapping provides a fresh perspective, contributing significant insights and advancing the field.

While diffusion-based methods have shown impressive capabilities in capturing diverse and complex hairstyles, their ability to generate consistent and high-quality multi-view out puts-crucial for real-world applications such as digital humans and virtual avatars-remains underexplored. In this paper, we propose Stable-Hair v2, a novel diffusion-based multi-view hair transfer framework. To the best of our knowledge, this is the first work to leverage multiple-view diffusion models for robust, high-fidelity, and view-consistent hair transfer across multiple perspectives. We introduce a comprehensive multi-view training data generation pipeline to generate high-quality triplet data, including bald images, reference hairstyles, and view-aligned source-bald pairs. Our multi-view hair transfer model integrates polar-azimuth embeddings for pose conditioning and temporal attention layers to ensure smooth transitions between views. To optimize this model, we design a novel multi-stage training strategy consisting of Pose-Controllable Latent IdentityNet training, Hair Extractor training, and Temporal Attention training. Extensive experiments demonstrate that our method accurately transfers detailed and realistic hairstyles to source subjects while achieving seamless and consistent results across views, significantly outperforming existing methods and establishing a new benchmark in multi-view hair transfer. Code is publicly available at https://github.com/sunkymepro/StableHairV2.

Cybersickness, or sickness caused by virtual reality (VR), represents a significant threat to the usability of VR applications. Repeated exposure to the same VR stimulus causes a reduction in cybersickness, referred to as Cybersickness Abatement from Repeated Exposure (CARE). This study examined whether the benefits of CARE generalize across distinct VR contexts, which was operationalized as three distinct games (a climbing game, a puzzle game, and a stealth survival game). Participants played a VR game for up to 20 minutes. Those in the Repeated Exposure condition played one VR game (either a puzzle game or a climbing game) on three separate days followed by a different VR game (a survival game) on the fourth day. Those in the Single Exposure condition played the survival game once. The three games all differed in several ways, including environment and task, whereas the puzzle and survival games shared a similar joystick locomotion interface that differed from the locomotion interface in the climbing game. Results indicate that cybersickness on Day 4 of the Repeated Exposure condition was significantly lower than that in the Single Exposure condition, regardless of which game was experienced on Days 1-3. The practical implication of this finding is that CARE that occurs in one VR context can generalize to a novel context with a distinct environment, task, and locomotion interface. Results are considered in the context of multiple theoretical explanations for CARE, including sensory rearrangement and habituation. These results support systematic exposure as an approach to reducing cybersickness.

Urban drainage systems, often designed for out dated rainfall assumptions, are increasingly unable to cope with extreme rainfall events. This leads to flooding, infrastructure damage, and economic losses, necessitating effective diagnostic and improvement strategies. In current practice, conventional analysis platforms built on hydrological-hydraulic models provide only limited analytical support, making it difficult to pin point defects, inspect causal mechanisms, or evaluate alternative design options in an integrated manner. In this paper, we develop DrainScope, to our knowledge, the first visual analytics approach for comprehensive diagnosis and iterative improvement of urban drainage systems. Defects are initially observed in the map view, after which DrainScope extracts the critical sub-systems associated with them using a rule-based search strategy, enabling focused analysis. It introduces a novel drainage-oriented Sankey diagram to visualize internal flow dynamics within the focused, static drainage system, revealing the causes of identified system defects. Furthermore, it enables flexible modification of drainage components corresponding to identified defects, coupled with a comparison view for rapid, iterative evaluation of improvement plans. We evaluate DrainScope through a real-world case study and positive feedback collected from domain experts.