IEEE transactions on visualization and computer graphics最新文献_第8页

Investigating 3D Selection Performance While Running in Extended Reality: an In-depth Study of the Effect of Speed. 在扩展现实中运行时调查3D选择性能：速度效应的深入研究。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-08-12 DOI: 10.1109/TVCG.2026.3722681

Ang Li, Jarrod Knibbe, Kiichiro Tatsuzawa, Gianluca Demartini, Stephen Viller, Guy Wallis, Wolfgang Stuerzlinger, Maxime Cordeil

{"title":"Investigating 3D Selection Performance While Running in Extended Reality: an In-depth Study of the Effect of Speed.","authors":"Ang Li, Jarrod Knibbe, Kiichiro Tatsuzawa, Gianluca Demartini, Stephen Viller, Guy Wallis, Wolfgang Stuerzlinger, Maxime Cordeil","doi":"10.1109/TVCG.2026.3722681","DOIUrl":"10.1109/TVCG.2026.3722681","url":null,"abstract":"We explore how running speed affects target selection in immersive environments. Through a Fitts' tapping task, we investigate direct touch selections while participants are standing or running (at speeds up to 9 km/h). We conduct a multifaceted controlled study (n=22) to understand the effect of speed, pointing phase, and foot-strike on selection performance. We find that speed dramatically increases movement time, error rate, perceived exertion, and task load. The increased movement time is driven by the correction phase, which doubles in duration at 9 km/h, while the ballistic phase remains stable. Our exploratory analysis further reveals that a higher cadence reduces the error rate at lower speeds (4.5 km/h), while this effect disappears at higher speeds (9 km/h), as participants' motor control in target selection is significantly disrupted by the movement oscillations. As the selection error rate quickly exceeds 30% when speed increases, even with accurate, fast external tracking, we argue that direct touch interaction is likely inappropriate for running. Further efforts are needed to facilitate selection interaction at higher running speeds.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148723894","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}

引用次数: 0

PeCE: A Visual Analytics Paradigm for Enhancing Counterfactual Explanations. PeCE：增强反事实解释的可视化分析范式。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-08-11 DOI: 10.1109/TVCG.2026.3722507

Qiang Lu, Hongfeng Wu, Sangui Jian, Xueyu Luo, Youwen Kong, Ye Yu, Wenxing Lu

{"title":"PeCE: A Visual Analytics Paradigm for Enhancing Counterfactual Explanations.","authors":"Qiang Lu, Hongfeng Wu, Sangui Jian, Xueyu Luo, Youwen Kong, Ye Yu, Wenxing Lu","doi":"10.1109/TVCG.2026.3722507","DOIUrl":"10.1109/TVCG.2026.3722507","url":null,"abstract":"Counterfactual explanations offer an intuitive way to understand the prediction behavior of machine learning models. However, they still face major challenges in practice. Explanation quality is often unclear due to feature redundancy and the lack of systematic evaluation. The resulting information is fragmented and hard to integrate into a coherent decision logic. To address these issues, this paper proposes a new analysis paradigm. It reframes counterfactual explanation as an auditable and iterative investigative reasoning workflow. The paradigm consists of three tightly coupled steps. First, it focuses on causal features to reduce the initial complexity of the explanation space. This is achieved through the Minimal Feature Boundary (MFB) and interactive constraint modeling. Second, it introduces multi-dimensional quality audit views. These views incorporate metrics such as the Counterfactual Equilibrated Quality Score (CEQS). They support evidence-based filtering and comparison of counterfactual candidates. Third, it establishes a visualization-driven hypothesis testing loop. This loop links coordinated views to distribution comparison and causal exploration. It allows users to dynamically validate and iteratively refine their understanding of model's behavior. The paradigm is instantiated in the visual analytics system PeCE. Its effectiveness is demonstrated through case studies and expert interviews. The results show that the proposed paradigm improves transparency and traceability in the counterfactual explanation process. As a result, counterfactual explanations become more credible and practical as diagnostic tools.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148714774","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}

引用次数: 0

CC-4DGS: Computational Deformation and Point-Cloud Compression for Storage-Efficient Dynamic Gaussian Splatting. 高效存储动态高斯飞溅的计算变形和点云压缩。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-08-06 DOI: 10.1109/TVCG.2026.3721136

Kyungdae Park, Chae Eun Rhee

{"title":"CC-4DGS: Computational Deformation and Point-Cloud Compression for Storage-Efficient Dynamic Gaussian Splatting.","authors":"Kyungdae Park, Chae Eun Rhee","doi":"10.1109/TVCG.2026.3721136","DOIUrl":"10.1109/TVCG.2026.3721136","url":null,"abstract":"Dynamic four-dimensional (4D) Gaussian Splatting has emerged as a powerful explicit representation for highquality view synthesis, yet existing methods still require tens to hundreds of megabytes per scene due to their heavy reliance on large multi-resolution hash tables and high-dimensional Gaussian attributes. This paper presents CC-4DGS, a storage-efficient and scalable framework that rethinks both deformation modeling and canonical attribute storage. First, we introduce a computational deformation field (CDF) that replaces large multi-resolution learnable hash tables with deterministic dense hash encoding and compact neural decoders, enabling on-the-fly synthesis of deformation features while reducing deformation storage to only 1-3 MB per scene. Second, we propose a compression of canonical point-cloud attributes (CCA) pipeline that compresses highdimensional spherical harmonic appearance terms and auxiliary Gaussian attributes via conditional autoencoding, selective quantization, and residual codebooks, achieving 3-5× point-cloud reduction with negligible quality loss. Together, these components yield a unified representation that preserves real-time rendering performance while reducing total storage to 20-30 MB. Extensive experiments across the N3DV and Technicolor Light Field datasets demonstrate that CC-4DGS achieves reconstruction accuracy comparable to state-of-the-art methods such as Swift4D, while offering significantly improved storage efficiency and favorable runtime-memory trade-offs.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687201","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}

引用次数: 0

PERCEIV: A Multimodal Physiological Dataset of Visual Encodings for Adaptive InfoVis Interfaces. 一个多模态生理数据集的视觉编码自适应InfoVis接口。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-08-06 DOI: 10.1109/TVCG.2026.3721212

Sebastian Idesis, Mireia Masias Bruns, Angela Lopez Cardona, Parvin Emami, Saravanakumar Duraisamy, Luis A Leiva, Ioannis Arapakis

{"title":"PERCEIV: A Multimodal Physiological Dataset of Visual Encodings for Adaptive InfoVis Interfaces.","authors":"Sebastian Idesis, Mireia Masias Bruns, Angela Lopez Cardona, Parvin Emami, Saravanakumar Duraisamy, Luis A Leiva, Ioannis Arapakis","doi":"10.1109/TVCG.2026.3721212","DOIUrl":"10.1109/TVCG.2026.3721212","url":null,"abstract":"We contribute PERCEIV (PERCeption of visual Encodings in InfoVis), a large-scale dataset to support studies of user responses to visual encoding variants as a foundation for adaptive information visualization interfaces. The dataset includes recordings from 120 participants who completed tasks of varying difficulty, while simultaneous multimodal data were collected from brain, eye, and electrodermal activity. All data are time-synchronized and accompanied by relevant annotations and participant metadata. We release raw sensor streams together with fully processed event-aligned derivatives and rich trial-level annotations. We also provide baseline analyses and scripts for ex tracting cognitive load features across modalities. In addition, we make the code for data pre-processing, feature extraction, qual ity control, and training/evaluating baseline Machine Learning classifiers available. Standardized data splits and comprehensive documentation further enable reproducible benchmarking and rapid reuse. We hope our dataset will facilitate novel studies of sensor modalities, development of computational models, and deeper understanding of cognitive state dynamics in controlled information-processing contexts.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687232","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}

引用次数: 0

Spatio-Temporal Kernel Density Estimation for Streaming Time-Varying Data. 时变数据流的时空核密度估计。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-08-06 DOI: 10.1109/TVCG.2026.3721513

Aritra Bhowmick

{"title":"Spatio-Temporal Kernel Density Estimation for Streaming Time-Varying Data.","authors":"Aritra Bhowmick","doi":"10.1109/TVCG.2026.3721513","DOIUrl":"10.1109/TVCG.2026.3721513","url":null,"abstract":"Kernel density estimation (KDE) is a fundamental tool across statistics, data science, visualization and machine learning. In particular, it is widely used in analyzing and visualizing multi-dimensional data sets, including, e.g., geo-spatial data. Spatio-temporal KDE is an important extension to the basic KDE problem that also takes into account the temporal relation of the data points, and provides a method to visualize evolving data patterns over time. With the explosive growth of Big Data in both size and complexity, it is typically not feasible to run naive exact algorithms due to the extremely high run time and memory-space requirements. Especially challenging is the streaming setting where the data points arrive in an online fashion, one time step at a time, and we can only access the data in one pass with a fixed, sub-linear memory. Such a challenging setting renders most of the existing methods to be inadmissible. In this paper, we take on this challenge by providing scalable approximate frameworks with low memory footprints under the streaming setting. We present randomized algorithms for efficient computation of spatio-temporal KDE with strong theoretical guarantees and empirical support. Specifically, we introduce a weighted sampling scheme and discuss a random-feature-based sketching method, and analyze their complexity and use cases. The proposed methods are sub-linear in memory and do not require the knowledge of the length of the data stream in advance. Also, the methods provide nice trade-offs between speed and accuracy. Moreover, the sketching method can easily support deletions of data points from the stream, which is not trivial for most sampling methods to perform robustly. In addition, we show how the sketching method can be easily used to answer aggregate density queries, with a computational advantage over any sampling approaches. Experiments on synthetic and real world datasets demonstrate the quality and efficiency of these proposed techniques.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687148","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}

引用次数: 0

Geometry-Semantics Co-Regularization for Gaussian Splatting in Indoor Reconstruction. 室内重建中高斯飞溅的几何-语义协同正则化。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-07-30 DOI: 10.1109/TVCG.2026.3718564

Haihong Xiao, Jianan Zou, Yanan Zhang, Wenxiong Kang, Ying He, Wei Jia

{"title":"Geometry-Semantics Co-Regularization for Gaussian Splatting in Indoor Reconstruction.","authors":"Haihong Xiao, Jianan Zou, Yanan Zhang, Wenxiong Kang, Ying He, Wei Jia","doi":"10.1109/TVCG.2026.3718564","DOIUrl":"10.1109/TVCG.2026.3718564","url":null,"abstract":"Recent advances in 3D Gaussian Splatting (3DGS) have significantly advanced indoor scene reconstruction, a key capability for AR/VR, robotics, and autonomous systems. However, existing methods that rely on 2D monocular priors often produce artifacts such as holes and unnatural protrusions due to insufficient or weak constraints. To address this limitation, we propose a geometry-semantics co-regularization framework that jointly optimizes geometry and semantics within 3DGS. On the geometric side, we introduce a multi-level geometric optimization strategy with two key contributions. First, inspired by neural implicit surface representations, we design a dual implicit architecture that integrates Implicit Moving Least Squares (IMLS) and Signed Distance Functions (SDFs). This structure enables mutual reinforcement between the two representations via local geometric approximation and global normal constraints, improving fine-grained surface modeling. Second, we develop a view-dependent normal consistency constraint that combines 2D observations with SDF gradients to refine surface accuracy. On the semantic side, we develop a multi-view semantic consistency supervision to regularize the semantic distributions of Gaussian primitives, ensuring cross-view consistency for Gaussians corresponding to the same semantic category or instance. Extensive experiments on the Replica and MuSHRoom datasets demonstrate that our approach achieves state-of-the-art geometric reconstruction quality and rendering fidelity.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148633374","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}

引用次数: 0

DVD: Scaffolding Non-experts' Ideation of Data Videos through Co-creation with AI. DVD：搭建非专家通过与人工智能共同创作的数据视频构思。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-07-29 DOI: 10.1109/TVCG.2026.3717858

Xiaozhu Hu, Yuchao Zhuo, Bingyuan Wang, Zeyu Wang, Mingming Fan, Tristan Braud, Xian Xu

{"title":"DVD: Scaffolding Non-experts' Ideation of Data Videos through Co-creation with AI.","authors":"Xiaozhu Hu, Yuchao Zhuo, Bingyuan Wang, Zeyu Wang, Mingming Fan, Tristan Braud, Xian Xu","doi":"10.1109/TVCG.2026.3717858","DOIUrl":"10.1109/TVCG.2026.3717858","url":null,"abstract":"Data videos are an increasingly popular storytelling medium, effectively communicating data-driven insights to diverse audiences. However, designing compelling data videos requires not only domain knowledge of the data but also expertise in cinematic design, posing substantial challenges for non-experts in design. To study how AI can support non-experts in addressing such challenges during early-stage design, we introduce ideate-through-cocreate, a design concept in which users' ideation is scaffolded through co-creation with generative AI. We instantiate this concept by proposing Data Video Designer (DVD), a proof-of-concept system that supports the ideation of data video opening scenes. DVD facilitates non-experts' ideation processes by generating exemplary video scripts and visuals from high-level topic and data summaries, referencing relevant design guidelines, and integrating accurate visualizations derived from their own data into the generated scenes. Through this workflow, DVD turns abstract cinematic guidelines and AI-generated materials into actionable ideation support. A workshop and a comparative study demonstrated the usefulness of the structured co-creation support provided by DVD within the scope of opening-scene design and revealed the creative potential in balancing the data authenticity and stylized expression. These findings provide initial evidence for the potential of structured human-AI co-creation to support data video ideation.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148623322","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}

引用次数: 0

Consistent 4D Appearance Editing with Gaussian Splatting. 一致的4D外观编辑高斯飞溅。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-07-28 DOI: 10.1109/TVCG.2026.3717152

Xiaosheng He, Fenglin Liu, Lin Gao, Yu-Kun Lai, Zhongang Cai, Lei Yang, Yi Xu, Guosheng Lin

{"title":"Consistent 4D Appearance Editing with Gaussian Splatting.","authors":"Xiaosheng He, Fenglin Liu, Lin Gao, Yu-Kun Lai, Zhongang Cai, Lei Yang, Yi Xu, Guosheng Lin","doi":"10.1109/TVCG.2026.3717152","DOIUrl":"10.1109/TVCG.2026.3717152","url":null,"abstract":"Editing dynamic scenes with 4D Gaussian Splatting (4DGS) is often hampered by spatiotemporal inconsistencies, or \"Gaussian drifting\", which degrades edit quality and temporal coherence. We identify that these artifacts stem from two distinct sources: foundational inaccuracies in the initial scene reconstruction, and the disruption of learned trajectories during the editing process itself. To address this, we propose a comprehensive framework that systematically tackles both sources of inconsistency. To solve reconstruction-induced errors, we introduce a novel prior-guided, multi-stage reconstruction pipeline that fuses geometric and motion priors to build a physically plausible and temporally stable foundation. To solve editing-induced errors, we further apply a universal trajectory-preserving technique, which safeguards high-quality motion by decoupling the appearance optimization from the learned deformation. Experiments demonstrate that by systematically addressing both the reconstruction and editing phases, our method achieves state-of-the-art, temporally consistent editing on a wide range of dynamic scenes where previous monolithic approaches fail.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148611321","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}

引用次数: 0

Signal or Noise? How User Movement and Sensor Placement Impact Physiological Data Collection in 6DoF Virtual Reality. 信号还是噪音？用户运动和传感器放置如何影响6DoF虚拟现实的生理数据收集。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-07-20 DOI: 10.1109/TVCG.2026.3715380

Matthieu Blanchard, Bertrand Massot, Pierre Raimbaud, Guillaume Lavoue

{"title":"Signal or Noise? How User Movement and Sensor Placement Impact Physiological Data Collection in 6DoF Virtual Reality.","authors":"Matthieu Blanchard, Bertrand Massot, Pierre Raimbaud, Guillaume Lavoue","doi":"10.1109/TVCG.2026.3715380","DOIUrl":"10.1109/TVCG.2026.3715380","url":null,"abstract":"To evaluate user experience in Virtual Reality (VR), researchers are increasingly using physiological data, such as electrocardiograms (ECG) and electrodermal activity (EDA), in conjunction with questionnaires. However, in 6-Degrees-of-Freedom VR, user movements and interactions can introduce noise on captured signals, making them potentially unusable. This noise depends on the movements performed and on sensor positions. Unfortunately, no study has addressed this issue, significantly hindering the effective use of physiological data in VR. To address this gap, we conducted a user study to evaluate the effects of sensor positions and user movements on signal quality, as well as sensor comfort and intrusiveness. We compared three positions for EDA and two for ECG on 36 users, who performed a series of five gestures. Results indicate that positioning EDA sensors on the palm offers the best balance between signal quality and user comfort. For ECG, a position closer to the heart is better. Most tested movements affect quality, with the worst being when users close their hand (for ECG and EDA) and move their arm (for ECG), where sensors are located. Based on these findings, we provide recommendations for the effective use of EDA and ECG sensors in 6DoF VR.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148537571","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}

引用次数: 0

FunHOI: Annotation-Free 3D Hand-Object Interaction Generation via Functional Text Guidance. FunHOI：通过功能文本引导生成无注释的3D手-对象交互。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-07-10 DOI: 10.1109/TVCG.2026.3712181

Yongqi Tian, Xueyu Sun, Haoyuan He, Jianlei Wang, Caigui Jiang

{"title":"FunHOI: Annotation-Free 3D Hand-Object Interaction Generation via Functional Text Guidance.","authors":"Yongqi Tian, Xueyu Sun, Haoyuan He, Jianlei Wang, Caigui Jiang","doi":"10.1109/TVCG.2026.3712181","DOIUrl":"10.1109/TVCG.2026.3712181","url":null,"abstract":"Hand-object interaction (HOI) is central to human manipulation, but synthesizing functional 3D HOI remains challenging due to dexterous hand motion, complex contact patterns, and strong geometric ambiguity. Existing methods often rely on 3D HOI annotations, predefined object templates, or supervised interaction priors. Such requirements limit their applicability to open-ended functional grasping scenarios, where the same object may require different contact regions and poses depending on the intended use. We present FunHOI, an annotation-free two-stage framework for functional-intent-conditioned 3D HOI synthesis from natural-language prompts. FunHOI represents each prompt using action-object-purpose semantics and first translates the functional intent into a semantically aligned 2D HOI guidance image through the Functional Grasp Generator (FGG). Rather than learning a direct text-to-3D generative prior, FunHOI reconstructs the hand and object from this 2D semantic guidance and composes them in 3D using the Functional Grasp Refiner (FGR), which performs scale-aware alignment, object pose approximation, and contact-driven refinement to improve spatial consistency and physical plausibility. Extensive experiments show that FunHOI achieves competitive reconstruction quality, improved hand-object contact plausibility, and better alignment with functional intent, without requiring 3D HOI annotations.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148426648","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}

引用次数: 0