IEEE transactions on visualization and computer graphics最新文献

Efficient Large-Scale Scene Reconstruction via Semantic-Aware Hybrid Representation. 基于语义感知混合表示的高效大规模场景重构。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-05-08 DOI: 10.1109/TVCG.2026.3691600

Husen Li, Jingyu Lin, Yudong Guo, Renjie Chen

{"title":"Efficient Large-Scale Scene Reconstruction via Semantic-Aware Hybrid Representation.","authors":"Husen Li, Jingyu Lin, Yudong Guo, Renjie Chen","doi":"10.1109/TVCG.2026.3691600","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3691600","url":null,"abstract":"Reconstructing large-scale 3D scenes remains challenging due to the need to balance photorealistic quality, real-time rendering, and compact storage. Recent progress in 3D Gaussian Splatting (3DGS) has achieved impressive fidelity and speed, yet its large-scale application suffers from excessive primitive counts, leading to prohibitive storage and rendering costs. To overcome this inefficiency, we introduce a novel semantic-guided hybrid representation that unifies textured meshes and 3D Gaussians in a differentiable framework. The key idea is to leverage meshes for geometrically regular regions such as roads and building facades, while reserving Gaussians for fine, complex details like vegetation. Our method is realized through three key technical contributions. First, we develop a semantic-guided adaptive modeling pipeline that fuses multi-view segmentation onto the scene mesh to robustly partition the scene and prune redundant Gaussians. Second, we introduce a high-performance CUDA-based hybrid renderer that seamlessly combines mesh rasterization with Gaussian splatting, enabling correct occlusion handling and joint optimization of both representations. Finally, we propose a mesh-guided sampling strategy that adaptively adds Gaussians to recover fine details in under-reconstructed areas. Extensive experiments on diverse large-scale datasets demonstrate that our approach significantly reduces storage requirements and accelerates rendering performance while maintaining comparable or superior visual quality.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147857878","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

NRRS: Neural Russian Roulette and Splitting. 神经俄罗斯轮盘赌和分裂。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-05-08 DOI: 10.1109/TVCG.2026.3691565

Haojie Jin, Jierui Ren, Yisong Chen, Guoping Wang, Sheng Li

{"title":"NRRS: Neural Russian Roulette and Splitting.","authors":"Haojie Jin, Jierui Ren, Yisong Chen, Guoping Wang, Sheng Li","doi":"10.1109/TVCG.2026.3691565","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3691565","url":null,"abstract":"We propose a novel framework for Russian Roulette and Splitting (RRS) tailored to wavefront path tracing, a highly parallel rendering architecture that processes path states in batched, stage-wise execution for efficient GPU utilization. Traditional RRS methods, with unpredictable path counts, are fundamentally incompatible with wavefront's preallocated memory and scheduling requirements. To resolve this, we introduce a normalized RRS formulation with a bounded path count, enabling stable and memory-efficient execution. Furthermore, we pioneer the use of neural networks to learn RRS factors, presenting two models: NRRS and AID-NRRS. At a high level, both feature a carefully designed RRSNet that explicitly incorporates RRS normalization, with only subtle differences in their implementation. To balance computational cost and inference accuracy, we introduce Mix-Depth, a path-depth-aware mechanism that adaptively regulates neural evaluation, further improving efficiency. Extensive experiments demonstrate that our method outperforms traditional heuristics and recent RRS techniques in both rendering quality and performance across a variety of complex scenes.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147857832","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

SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors. SVGS：使用具有空间变化颜色的原语增强高斯飞溅。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-05-07 DOI: 10.1109/TVCG.2026.3690745

Rui Xu, Wenyue Chen, Jiepeng Wang, Yuan Liu, Peng Wang, Cheng Lin, Shiqing Xin, Xin Li, Wenping Wang, Taku Komura

{"title":"SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors.","authors":"Rui Xu, Wenyue Chen, Jiepeng Wang, Yuan Liu, Peng Wang, Cheng Lin, Shiqing Xin, Xin Li, Wenping Wang, Taku Komura","doi":"10.1109/TVCG.2026.3690745","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3690745","url":null,"abstract":"Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non compact representation. In this paper, we introduce a new method called SVGS (Spatially Varying Gaussian Splatting) that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability. We have implemented bilinear interpolation, movable kernels, and tiny neural networks as spatially varying functions. SVGS employs 2D Gaussian surfels as primitives, which significantly enhances novel-view synthesis while maintaining high-quality geometric reconstruction. This approach is particularly effective in practical applications, as scenes combining complex textures with relatively simple geometry occur frequently in real-world environments. Quantitative and qualitative experimental results demonstrate that all three functions outperform the baseline, with the best movable kernels achieving superior novel view synthesis performance on multiple datasets, highlighting the strong potential of spatially varying functions.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147847829","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

SelfBlending: Artificial Intelligence-driven Augmentation with Hand Interactions for Seamless Reality Blending in Virtual Environments. 自混合：人工智能驱动的增强与手交互在虚拟环境中无缝的现实混合。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-05-06 DOI: 10.1109/TVCG.2026.3690947

Ahmed Elsharkawy, Bocheon Gim, Aya Ataya, SeungJun Kim

{"title":"SelfBlending: Artificial Intelligence-driven Augmentation with Hand Interactions for Seamless Reality Blending in Virtual Environments.","authors":"Ahmed Elsharkawy, Bocheon Gim, Aya Ataya, SeungJun Kim","doi":"10.1109/TVCG.2026.3690947","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3690947","url":null,"abstract":"Accessing real-world objects during immersive virtual reality (VR) experiences remains challenging, as current cross-reality systems often rely on predefined interaction steps, tracking devices/markers, or fixed object setups. They also lack support for personalized object recall, where users can add, remove, or modify real-world items blended into the virtual environment (VE). Many head-mounted displays (HMDs) include passthrough technology to switch between virtual and real worlds, but it often disrupts immersion by requiring a full shift from virtual to real. Thus, maintaining an optimal balance between virtuality and reality is difficult. To address these challenges, we developed SelfBlending, a framework that uses AI-based hand tracking to let users label physical objects through freehand gestures, then blends the selected item into the VE using object recognition, enabling interaction with the relevant real-world object. SelfBlending was evaluated against two common interaction conditions: the default passthrough feature in VR HMDs and the conventional approach of physically removing the HMD to access real-world objects. Results from seated, single-object interactions with tabletop-placed items showed that SelfBlending enhanced user experience by boosting presence, supporting efficient physical interaction, and improving cross-reality continuity. It also enabled selective interaction with real objects while minimizing the disruption of VR experience.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147847809","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

Expressive Head Avatar Modeling from Monocular Video of Neutral Expression. 基于中性表情单目视频的表情头像建模。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-05-05 DOI: 10.1109/TVCG.2026.3690559

Qing Chang, Yao-Xiang Ding, Kun Zhou

{"title":"Expressive Head Avatar Modeling from Monocular Video of Neutral Expression.","authors":"Qing Chang, Yao-Xiang Ding, Kun Zhou","doi":"10.1109/TVCG.2026.3690559","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3690559","url":null,"abstract":"We study the reconstruction of high-quality 3D head avatars. Our goal is to reduce the reliance on dense capture data required by most existing approaches, which limits their practicality. Recent advances have attempted to address this using single or few input images by either training a prior model or fine-tuning multi-view diffusion models to generate pseudo training points. However, these methods fall short in producing multi-view-consistent, high-fidelity results aligned with the input data. This motivates us to explore a more practical and user-friendly input setting. Modern smartphones such as Apple's Face ID already guide users to slowly rotate their heads in front of a single camera, enabling the capture of facial data across varying viewpoints with minimal effort. This simple and intuitive scanning motion has become a widely accepted user habit and provides sufficient geometric information-highlighting a natural opportunity for 3D head avatar creation from monocular videos of neutral expression. In this paper, we introduce R $^{2}$ Avatar, a lightweight and user-friendly framework for generating expressive 3D head avatars under this setting. Our method adopts a Reconstruction-by-Restoration strategy that avoids large-scale model pretraining while achieving high-quality animatable avatars. Specifically, a geometry-guided warping module first synthesizes coarse expression variations from the neutral input. Then, a restoration module refines the warped results by recovering high-frequency facial details, including mouth interior, with the help of a data-driven 2D animation prior. These restored images serve as supervision targets to optimize the final avatar. Experiments demonstrate that our method produces realistic avatars with improved expression diversity and view consistency compared to baseline approaches. Our Code and data will be released upon acceptance.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147847747","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-Aware Scene Configurations for Novel View Synthesis. 新颖视图合成的几何感知场景配置。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-05-05 DOI: 10.1109/TVCG.2026.3690462

Minkwan Kim, Changwoon Choi, Young Min Kim

引用次数: 0

ChartBlender: an Interactive System for Authoring and Synchronizing Visualization Charts in Video. ChartBlender：一个用于创作和同步视频可视化图表的交互式系统。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-05-04 DOI: 10.1109/TVCG.2026.3689056

Yi He, Yuqi Liu, Chenpu Li, Ruoyan Chen, Chuer Chen, Shengqi Dang, Nan Cao

{"title":"ChartBlender: an Interactive System for Authoring and Synchronizing Visualization Charts in Video.","authors":"Yi He, Yuqi Liu, Chenpu Li, Ruoyan Chen, Chuer Chen, Shengqi Dang, Nan Cao","doi":"10.1109/TVCG.2026.3689056","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3689056","url":null,"abstract":"Embedded data visualizations have emerged as a powerful narrative medium for conveying complex information within video footage. However, creating such content remains labor-intensive, as existing workflows rely on manual frame-by-frame adjustments to en sure spatial and temporal consistency. To address these challenges, we present ChartBlender, an interactive authoring system designed to streamline the creation, embedding, and automatic synchronization of data visualizations within video scenes. We develop a tracking pipeline that supports both object and camera tracking, ensuring robust alignment of visualizations with dynamic video content. To maintain visual clarity and aesthetic coherence, we also explore the design space of video-suited visualizations and develop a library of customizable templates optimized for video embedding. We evaluated ChartBlender through two controlled experiments and expert interviews with five do main experts. Results show that our system enables accurate synchronization and accelerates the production of data-driven videos.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147847730","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

Dynamic Global Illumination for Interactive Gaussian Splatting Scenes in Real Time. 实时交互高斯溅射场景的动态全局照明。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-05-04 DOI: 10.1109/TVCG.2026.3689199

Chenxiao Hu, Meng Gai, Guoping Wang, Sheng Li

{"title":"Dynamic Global Illumination for Interactive Gaussian Splatting Scenes in Real Time.","authors":"Chenxiao Hu, Meng Gai, Guoping Wang, Sheng Li","doi":"10.1109/TVCG.2026.3689199","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3689199","url":null,"abstract":"We present a real-time pipeline to approximate global illumination in interactive or dynamic scenes, including both 3D Gaussian models and conventional meshes. Building on a formulated surface light transport model for 3D Gaussians, we address key performance challenges through a fast compound stochastic ray-tracing algorithm and a hardware 3D Gaussian rasterizer, and we implement multiple RTGI (real-time global illumination) techniques for 3D Gaussians. Our pipeline enables real-time rendering of interactive scenes featuring editable materials, lights, meshes, and 3D Gaussian models, effectively capturing multi-bounce diffuse and one-bounce glossy light transport. Our approach covers a wide range of dynamic light sources, including area lights, directional lights, and environmental lighting. Comprehensive experimental results demonstrate that our approach can efficiently render global illumination for both 3DGS models and hybrid models combining meshes and 3DGS, all in real time. Our pipeline highlights the potential of 3D Gaussians in real-time global illumination, and offers insights into performance optimization.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147847738","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

Strunkmap: An Abstract Approach to Understand Spatiotemporal Density Distribution. Strunkmap：一种理解时空密度分布的抽象方法。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-05-04 DOI: 10.1109/TVCG.2026.3689880

Xin Wang, Jingyuan Zhang, Lei Yu, Zhirong Huang, Jiajia Ma, Shiqi Cheng, Ruize Zhou, Xiaoxiao Ma, Jia Xu, Peng Wang, Li Yang, Fengjun Zhang

{"title":"Strunkmap: An Abstract Approach to Understand Spatiotemporal Density Distribution.","authors":"Xin Wang, Jingyuan Zhang, Lei Yu, Zhirong Huang, Jiajia Ma, Shiqi Cheng, Ruize Zhou, Xiaoxiao Ma, Jia Xu, Peng Wang, Li Yang, Fengjun Zhang","doi":"10.1109/TVCG.2026.3689880","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3689880","url":null,"abstract":"Visual analysis of spatiotemporal density distributions is crucial for understanding spatiotemporal dynamics. However, existing methods suffer from visual occlusion and information loss when simultaneously displaying multiple density distributions. We present Strunkmap as an abstract approach to address these challenges. We introduce anisotropic kernel density estimation to enhance the accuracy of density generation. We extract the trunks of density distributions to identify the overall spatial patterns. Path scanning and trunk-outline matching strategies are employed to preserve local spatial structure. We design a stacked trunk plot that enables lossless density representation while conserving substantial screen space. Based on the visual design, Strunkmap integrates multiple heatmaps within a single map to effectively display temporal evolution of density distributions without visual occlusion. Ablation studies and comparative experiments validate the superiority of Strunkmap in accuracy and efficiency for hotspot identification and trend exploration. Theoretical analysis demonstrates Strunkmap's scalability, which we further verify through large-scale spatiotemporal data visualization. Color encoding schemes and scaling ratios are discussed to illustrate the flexibility. Our evaluations with user feedback demonstrate that Strunkmap is a viable solution with significant potential to real-world applications.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147847755","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

Interactive Visual Exploration of Rule-Based Model Logic. 基于规则的模型逻辑的交互式可视化探索。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-05-01 DOI: 10.1109/TVCG.2026.3689736

Natalia Andrienko, Gennady Andrienko, Bahavathy Kathirgamanathan

{"title":"Interactive Visual Exploration of Rule-Based Model Logic.","authors":"Natalia Andrienko, Gennady Andrienko, Bahavathy Kathirgamanathan","doi":"10.1109/TVCG.2026.3689736","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3689736","url":null,"abstract":"Rule-based machine learning models, including those derived from decision trees or forests, are often considered inherently interpretable. However, human understanding is hindered by model size, rule complexity, and interdependencies between features. Moreover, rule sets extracted from ensemble models can contain contradictory, incomplete, or counterintuitive logic, even when the overall model achieves high predictive accuracy. This paper introduces a visual analytics methodology designed to support systematic exploration of rule-based model logic and its alignment with domain knowledge. Our approach integrates overview visualizations, interactive filtering, contradiction analysis, and topic modeling. This enables analysts to detect illogical or implausible rules, assess their potential impact, and refine the model to improve its interpretability and trustworthiness. A key distinction of our method is its ability to support reasoning about model behavior both with and without access to labeled data. We demonstrate the approach through two real-world case studies: evaluating logical consistency in a vessel movement classifier and analyzing feature relationships in a COVID-19 prediction model. These studies show how visual analytics can facilitate logic-focused model critique beyond traditional performance metrics and enable valuable domain-relevant insights.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825069","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