Jingtao Zhou,Xuan Gao,Dongyu Liu et al.
Jingtao Zhou et al.
We present GSwap, a novel consistent and realistic video head-swapping system empowered by dynamic neural Gaussian portrait priors, which significantly advances the state of the art in face and head replacement. Unlike previous methods that...
PortInput: Enabling Always-available Micro-gesture Input with Pressure Array Sensor [0.03%]
基于压力阵列传感器的永不干扰型微手势输入系统
Haiyan Jiang,Henry Been-Lirn Duh,Mingwei Hu et al.
Haiyan Jiang et al.
Micro-gestures provide a natural, efficient, and privacy-preserving input modality; however, existing techniques often depend on environmental conditions, limiting their robustness and applicability in real-world settings. In this work, we ...
Characterizing Device Transitions and Their Impact on Presence, Embodiment and Avatar Identification in Cross-Platform Virtual Environments [0.03%]
跨平台虚拟环境中设备转换及其对在场、具身感和化身识别影响的特征研究
Florian Dufresne,Geoffrey Gorisse,Olivier Christmann
Florian Dufresne
Cross-platform virtual environments allow users to experience interactive virtual places from a variety of peripherals, such as mobiles, computers or virtual reality headsets. These devices offer different interactivity and immersion levels...
Chenlu Zhan,Yufei Zhang,Gaoang Wang et al.
Chenlu Zhan et al.
Modeling 3D language fields with Gaussian Splatting for open-ended language queries has recently garnered increasing attention. However, recent 3DGS-based models leverage view-dependent 2D foundation models to refine 3D semantics but lack a...
Spatial Multiple Importance Sampling for Real-time Irradiance Probes [0.03%]
基于空间多重重要性采样的实时环境光探针生成算法研究
Tuo Chen,Zi-Heng Zhou,Lingqi Yan et al.
Tuo Chen et al.
Real-time global illumination rendered with low variance remains a persistent challenge. Many engines employ irradiance probes as a relatively cheap technique, but constrained computational budgets often lead to flickering artifacts in rend...
FISN: FInding Spatial Neighborhoods for Generalizable Novel View Synthesis [0.03%]
基于空间邻域查找的通用视点合成方法
Yanqi Bao,Tianyu Ding,Jing Huo et al.
Yanqi Bao et al.
We present FISN, a generalizable novel view synthesis algorithm that enables feedforward inference of Neural Radiance Fields (NeRF) or 3D Gaussian Splatting (3DGS) from reference images. Unlike existing work that either separately model the...
Look, Compare and Draw: Differential Query Transformer for Automatic Oil Painting [0.03%]
观、比、得、绘——自动油画生成的差分查询变换模型
Lingyu Liu,Yaxiong Wang,Li Zhu et al.
Lingyu Liu et al.
This work introduces a new approach to automatic oil painting that emphasizes the creation of dynamic and expressive brushstrokes. A pivotal challenge lies in mitigating the duplicate and common-place strokes, which often lead to less aesth...
NewsVis: GenAI-based Visual Storytelling for Corporate Financial News [0.03%]
基于GenAI的视觉叙事的企业财务新闻平台NewsVis
Jia Bu,Mingwei Jiang,Shuqi Liu et al.
Jia Bu et al.
Corporate financial news is pivotal for market decisions, but often overwhelms general audiences. While data videos effectively bridge this comprehension gap, their production remains a bottleneck for journalists. We present NewsVis, an aut...
A Probabilistic Approach to Understanding User Preferences for Adaptive Placement of AR Interfaces in Different Physical Environments [0.03%]
基于用户偏好的自适应放置AR界面的概率研究方法
Qiushi Zhou,Jean Paul Vera Soto,Zhongyi Bai et al.
Qiushi Zhou et al.
We develop a probabilistic approach to understanding user preferences for adaptive placement of augmented reality (AR) interfaces in the physical environment through a series of user studies conducted using simulated desktop and virtual rea...
Automatic Formation Generation based on Scene Awareness for Guided Group Navigation in VR [0.03%]
基于场景感知的VR群体导航布局生成方法
Jian Wu,Lili Wang,Zhikai Wen et al.
Jian Wu et al.
Group navigation is a virtual reality (VR) technology designed to replace personal navigation, enhancing efficiency and aiding guided tours in path planning for other users. Group navigation techniques require users to have a clear understa...