IEEE transactions on visualization and computer graphics最新文献

{"title":"LatRef-Diff: Latent and Reference-Guided Diffusion for Facial Attribute Editing and Style Manipulation.","authors":"Wenmin Huang, Weiqi Luo, Xiaochun Cao, Jiwu Huang","doi":"10.1109/TVCG.2026.3740083","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3740083","url":null,"abstract":"<p><p>Facial attribute editing and style manipulation are crucial for applications like virtual avatars and photo editing. However, achieving precise control over facial attributes without altering unrelated features is challenging due to the complexity of facial structures and the strong correlations between attributes. While conditional GANs have shown progress, they are limited by accuracy issues and training instability. Diffusion models, though promising, face challenges in style manipulation due to the limited expressiveness of semantic directions. In this paper, we propose LatRef-Diff, a novel diffusion-based framework that addresses these limitations. We replace the traditional semantic directions in diffusion models with style codes and propose two methods for generating them: latent and reference guidance. Based on these style codes, we design a style modulation module that integrates them into the target image, enabling both random and customized style manipulation. This module incorporates learnable vectors, cross-attention mechanisms, and a hierarchical design to improve accuracy and image quality. Additionally, to enhance training stability while eliminating the need for paired images (e.g., before and after editing), we propose a forward-backward consistency training strategy. This strategy first removes the target attribute approximately using image-specific semantic directions and then restores it via style modulation, guided by perceptual and classification losses. Extensive experiments on CelebA-HQ demonstrate that LatRef-Diff achieves state-of-the-art performance in both qualitative and quantitative evaluations. Ablation studies validate the effectiveness of our model's design choices.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149120581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diffusing Heat: Generative Scan Path Optimization for Laser Powder Bed Fusion.","authors":"Yuming Huang, Junhao Ding, Ting Li, Xu Song, Weiming Wang","doi":"10.1109/TVCG.2026.3738833","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3738833","url":null,"abstract":"<p><p>Island scanning is widely adopted in Laser Powder Bed Fusion (LPBF) to mitigate residual stress and distortion. The global visiting order of islands still governs the layer-wise thermal history. Existing geometric heuristics are efficient but largely ignore history-dependent heat accumulation on irregular topologies, while physics-driven global optimization requires repeated thermal evaluation and is typically computationally expensive for online planning. We present Diffusing Heat, a diffusion-model-based planner that generates heat-aware island sequences for complex layer geometries. We first couple a high throughput Gaussian-kernel thermal surrogate with simulated annealing to build an expert dataset under a long-horizon thermal-uniformity objective that penalizes both sustained non uniformity and peak overheating events. Conditioned on the set of active island centroids, a conditional diffusion model denoises a permutation-like successor representation in parallel and produces score matrices that are close to valid permutations. At inference time, sampled scores are decoded into feasible open scan paths and further improved by a lightweight objective consistent refinement stage under the same surrogate metric. Extensive simulated evaluations demonstrate that our planner consistently improves thermal uniformity over representative heuristic baselines, while approaching the solution quality of offline combinatorial optimization and accelerating the planning process by over 20 times. Furthermore, physical LPBF experiments show our planner reduces maximum distortion by up to 53% compared to standard geometric patterns.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149120606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of Turn-Taking Dialogues and Reverberation Features on Co-Immersion in Audio Augmented Virtuality.","authors":"Davide Fantini, Giovanni Bonfanti, Federico Avanzini, Giorgio Presti, Michele Geronazzo","doi":"10.1109/TVCG.2026.3739363","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3739363","url":null,"abstract":"<p><p>This study revises a prior Audio Augmented Virtuality (AAV) experiment on the co-immersion of virtual sound sources rendered with simplified late reverberation (LR) approaches. We investigate the effect of stimulus type by transitioning from overlapping speech to turn-taking dialogues, providing a more ecological context for remote communication. Participants listened to two, three, or four virtual speakers in turn-taking dialogues, dynamically rendered with Ambisonics Room Impulse Responses (RIRs) and individualized Head-Related Transfer Functions (HRTFs). In each trial, they were asked to detect and identify an impostor-a speaker rendered with one of two simplified static LR conditions. Compared to overlapping speech, turn-taking dialogues yielded more precise impostor identification when detected. Concurrently, listeners showed a stronger bias toward reporting the impostor's absence, suggesting that conversational engagement enhances the simulation's acceptability. An exploratory acoustic features analysis further revealed a shift toward clarity-related parameters in listener strategy. This work validates the co-immersion paradigm for assessing the acceptability of simplified audio rendering, offering guidelines for designing efficient yet realistic auditory experiences.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-Quality Depth-Adaptive Computer-Generated Hologram Using Depth-aware Plug-in Network.","authors":"Ganzhangqin Yuan, Zihan Geng","doi":"10.1109/TVCG.2026.3739374","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3739374","url":null,"abstract":"<p><p>Learning-based computer-generated holography (CGH) enables real-time hologram generation, but many existing methods are trained for a fixed propagation depth and require retraining when the target depth changes. Recent depth-adaptive approaches alleviate this limitation, yet often rely on specially designed architectures, limiting compatibility with existing CGH networks. We propose a depth-aware plug-in network that equips existing fixed-depth CGH models with depth-adaptive generation capability without modifying their backbones. The module performs intermediate feature modulation using a physics-guided signal derived from the optical transfer function (OTF), which captures propagation-dependent phase structures for effective depth adaptation. By decoupling depth modeling from network design, the proposed method can be flexibly integrated into diverse CGH frameworks with minimal overhead while avoiding the need for separate models at different propagation depths, thereby reducing the overall training cost. Experiments on multiple representative CGH backbones, together with ablation studies and optical validations, demonstrate consistently improved reconstruction quality and robust depth generalization across a wide range of propagation depths, offering a practical solution for generalizable depth-adaptive CGH systems .</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interactive Target Element Selection in Infographics Via Scene Tree Modeling.","authors":"Jiangning Zhu, Yuxing Zhou, Lei Li, Shixia Liu","doi":"10.1109/TVCG.2026.3738881","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3738881","url":null,"abstract":"<p><p>Accurately detecting infographic elements is essential for infographic understanding and generation. However, high-performance detection models rely on large-scale training datasets with precise bounding-box annotations for infographic elements, which are time-consuming to create manually. Although fine-tuned object detection models can predict candidate bounding boxes, they often include non-target elements to be filtered out and therefore require efficient target element selection. To address this challenge, we develop a human-in-the-loop tool, EleDetective, that combines automatic selection, coordinated visualizations, and interactive refinement. The key idea is to represent an infographic as a scene tree that captures the region hierarchy. Based on this representation, we formulate target element selection as a bilevel optimization problem to recover missed elements and remove misselected elements. Since automatic selection is not always perfect, we introduce a treemap-based grid visualization and a scene tree visualization to help users explore selection results and identify potential errors. Users then correct the identified errors, and their corrections are propagated across infographics based on query-sensitive similarity, improving the quality of selection at scale. Quantitative evaluation and two use cases demonstrate the effectiveness of our method.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149140004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HAGI++: Head-Assisted Gaze Imputation and Generation.","authors":"Chuhan Jiao, Zhiming Hu, Andreas Bulling","doi":"10.1109/TVCG.2026.3738876","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3738876","url":null,"abstract":"<p><p>Mobile eye-tracking is crucial for capturing human visual attention in real-world and XR settings, supporting research and human-computer interaction. Yet blinks, pupil-detection errors and lighting changes create missing values that hinder gaze analysis. We present HAGI++, a multi-modal diffusion-based imputation method that, for the first time, leverages integrated head-orientation sensors to exploit the natural correlation between head and eye movements. Using a transformer-based diffusion model, it learns cross-modal dependencies between eye and head data and can additionally incorporate wrist/hand motion when such wearable signals are available. Evaluations on the large-scale Nymeria, Ego-Exo4D and HOT3D datasets show that HAGI++ consistently outperforms traditional interpolation and deep-learning time-series imputation baselines. Statistical analysis confirms that its gaze-velocity distributions closely match real human behaviour, yielding realistic imputations. Even when 100% of gaze data are missing (pure gaze generation), HAGI++ exceeds methods that rely on the visual inputs and the methods rely on full-body motion capture by incorporating wrist motion from commercial wearables. Our approach enables more complete, accurate eye-gaze recordings in real-world contexts, enhancing gaze-based analysis and interaction across many applications.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hint-AUC: Deterministic Region-based Hint Generation for Line Art Colorization Evaluation.","authors":"Koki Madono, Yuan Mingcheng, Edgar Simo-Serra","doi":"10.1109/TVCG.2026.3738401","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3738401","url":null,"abstract":"<p><p>Line art colorization is an important design application that has been extensively studied in recent years. Focusing on usability, most approaches have been developed for interactive use where colors are specified using user hints. However, collecting a large dataset of user hints for training is challenging. As a result, a variety of approaches have emerged for generating hints for both training and evaluation, such as color dots and scribbles. Furthermore, the lack of a common evaluation framework, differences in hint generation implementations, and limited code availability reduce reproducibility. For these reasons, highly stochastic neural network-based algorithms have made it challenging to fairly evaluate and compare different approaches. In this paper, we introduce a novel evaluation framework for line art colorization algorithms that leverages deterministic regionbased hints inspired by human drawing behavior. Our framework enables in-depth, fair comparisons with existing colorization models. Moreover, the same generated hints can be incorporated into training a colorization model to significantly improve the quality of the colorization results, as shown in evaluations using both deterministically and randomly sampled hints. Our evaluation is consistent with the overall human-preference results, and training with the generated hints improves colorization quality.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacy.","authors":"Soohyun Lee, Jaeyoung Kim, Seokhyeon Park, Sihyeon Lee, Jiwon Song, Bohyoung Kim, Hyunjoo Song, Jinwook Seo","doi":"10.1109/TVCG.2026.3738844","DOIUrl":"10.1109/TVCG.2026.3738844","url":null,"abstract":"<p><p>Large Vision-Language Models (LVLMs) have shown remarkable capabilities in visualization interpretation, yet it remains unclear whether their responses reflect genuine reasoning over visual evidence or the influence of factual priors learned during training. Current evaluation methods mix these two sources, obscuring when correct visual interpretation is overridden by memorized factual knowledge. We present a disentanglement framework that systematically isolates visual correctness from factual correctness, revealing fundamental validity limitations in existing visualization literacy assessments. Through three complementary experiments with 15 state-of-theart LVLMs, we demonstrate that: (1) Although several models achieve human-level performance on standard tests (VLAT), such performance may reflect factual recall rather than visual understanding, whereas randomized-data tests (reVLAT) underestimate visualization literacy when visual interpretation is correct but superseded by conflicting factual priors. (2) Using our Counterfactual Visualization Literacy Assessment Test (CVLAT) alongside capability-normalized arbitration metrics, we classify models by the sign of their visual-factual reliance index (VFRI). This classification reveals a visualization-oriented majority and a factual knowledge-oriented minority, although several near-zero cases warrant cautious interpretation. The factual knowledgeoriented minority tends to override the chart with prior knowledge. A human baseline (N = 30) on the same counterfactual items confirms that people overwhelmingly follow the chart under conflict, providing a human reference point for visual-factual arbitration. (3) Prompt-based intervention can shift this prioritization, but its effectiveness is highly model-dependent and often direction-asymmetric, with some models responding strongly to only one prompt direction. Furthermore, high chart-reading capability does not predict prompt-controllability, indicating that visual-factual arbitration is not uniformly steerable. Overall, our findings demonstrate that LVLMs' high visualization accuracy is not sufficient evidence of faithful visual reasoning. We argue that reliable LVLM integration into visual analytics requires evaluating not only visualization literacy, but also how models arbitrate between visual evidence and factual priors, particularly when the two sources diverge. The CVLAT benchmark and code are available at https://github.com/JaeyoungKim-HCIL/CVLAT.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149083262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Room to Roam: Real-Time Reset Prediction for Redirected Walking Based on Environment Layouts.","authors":"Sulim Chun, Ho Jung Lee, In-Kwon Lee","doi":"10.1109/TVCG.2026.3738775","DOIUrl":"10.1109/TVCG.2026.3738775","url":null,"abstract":"<p><p>Redirected Walking (RDW) allows users to explore large virtual environments by using overt resets to reorient users and prevent collisions. However, frequent resets increase the risk of cybersickness and reduce presence. Real physical environments are usually cluttered, and the complexity of their layouts affects the reset frequency. Physical spaces usually contain various objects, some fixed (e.g., built-ins) and some movable (e.g., furniture), creating opportunities to reduce the need for resets by rearranging movable objects. Systematically evaluating alternative layouts is challenging because repeated user testing is costly, and simulation-based approaches are often too slow for interactive design. We introduce a deep-learning predictor that estimates the expected number of resets directly from top view layout maps of physical and virtual environments. Trained on large-scale simulation data, the model generalizes to unseen layouts and provides interactive predictions at a rate of 105 milliseconds per layout. We embedded the predictor in a layout-editing interface and compared three interfaces (intuition-driven, simulation-based, and prediction-based) in a user study. Participants reached the pre-specified reset target with all three interfaces. With the prediction-based interface, they reached it in less time, with lower workload and higher usability. Additionally, consultations with four RDW experts emphasized effort, sequencing constraints, and object semantics, and recommended localized readouts showing where resets occur. These results suggest that continuous reset estimates reduce the time and workload needed to prepare a cluttered space for RDW.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149083274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stylized Sketch Synthesis Using Diffusion Priors and Structural Guidance.","authors":"Xiaonan Fang, Zhengfei Ren, Muhan Chang, Jiang Xin, Song-Hai Zhang","doi":"10.1109/TVCG.2026.3738459","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3738459","url":null,"abstract":"<p><p>Translating an image into a reference style is a widely studied problem. Sketches, as a family of highly abstract styles, are usually difficult to synthesize under general image stylization frameworks. A major challenge is that the reference style image could be semantically irrelevant to the content image. Based on recent advances in image stylization using diffusion models, we propose a novel stylized sketch synthesis algorithm that directly manipulates the latent code of the variational autoencoder using the priors of a pretrained diffusion model. In particular, we construct a unified attention distillation loss to align the self-attention layer features with content and style images. To maintain the semantic structures in the content image, we introduce a structural guidance for additional regularization. As for the guidance map, we adopt a dynamic vector sketch that is jointly optimized with the latent code. We also explore possible alternatives: using a fixed Canny edge map or using multiple guidance maps. We evaluated our method on a Diverse-Sketch-Stylization (DSS) dataset that includes various reference sketch styles and also conducted experiments on 4SKST, FS2K, and Anime datasets. The qualitative and quantitative results show that our method can transfer abstract sketch styles while faithfully conveying the original content.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149140006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}