Yang Li,Songlin Yang,Xiaoxuan Han et al.
Yang Li et al.
Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre-collected preferenc...
InfoLoD: Training-Data-Free Hierarchical 3D Gaussian Splatting via Fisher-Guided View Synthesis [0.03%]
InfoLoD:基于Fisher指引视图合成的无训练数据自由层次化3D高斯点生成器
Zhenyu Xia,Pengcheng Han,Lin Chen et al.
Zhenyu Xia et al.
Real-time visualization of massive 3D virtual environments, such as city-scale digital twins and immersive simulations, remains a core challenge in computer graphics. While 3D Gaussian Splatting (3DGS) achieves photorealistic rendering at i...
Bin Huang,Haoran Mo,Chengying Gao
Bin Huang
Line art colorization is a critical yet labor-intensive bottleneck in professional animation production, requiring artists to maintain rigorous color consistency across frames. While contemporary methods leveraging feature alignment or gene...
AnyTalk: Speech Animation for Arbitrary Characters Leveraging a Video Generation Model [0.03%]
AnyTalk:利用视频生成模型实现任意角色的语音动画
Kwan Yun,Serin Yoon,Sunjin Jung et al.
Kwan Yun et al.
We present AnyTalk, a novel method for generating 3D speech animations for arbitrary characters without requiring any animation data. While existing audio-driven 3D speech animation methods rely on character-specific training data or labori...
FMReward: Aligning and Evaluating Audio-Driven 3D Facial Animation with Human Preferences [0.03%]
基于人类偏好的音频驱动的三维面部动画的对齐与评估
Sijing Wu,Yunhao Li,Zhilin Gao et al.
Sijing Wu et al.
Audio-driven 3D facial animation is essential for advancing immersion and interactivity in virtual experiences. Although recent advances have shown promising capabilities, the training and evaluation of existing methods typically rely on gr...
Optimizing Few-Shot Novel View Synthesis with Human-Perceptual Preferences [0.03%]
基于人类感知偏好的少样本新视图合成优化
Xiaoyu Xu,Jiebin Yan,Sheyang Tang et al.
Xiaoyu Xu et al.
Novel view synthesis methods, such as neural radiance fields and 3D Gaussian splatting, offer a promising solution for photorealistic rendering. However, they remain challenged in few-shot settings, where models tend to overfit the limited ...
Efficient Predictive VR Interaction for Fine Teleoperation Using Physics-Based simulation and automatic planning [0.03%]
基于物理的仿真和自动规划的高效预测VR交互精细遥操作
Xinhai Wu,Tiantian Wang,Xinyu Zhang
Xinhai Wu
In complex and hazardous environments, robots often require human's fine teleoperation to ensure accurate decision-making and optimal manipulation. To improve teleoperation efficiency, we design and develop 3D predictive Virtual Reality (VR...
Beyond Upright VR: Understanding Direct Interaction and Hand Redirection Strategies in Supine Posture [0.03%]
仰卧姿势下的直接交互和手部重定向策略的研究超出了直立VR的范畴
Zhiqing Wu,Jiawei Li,Shumeng Zhang et al.
Zhiqing Wu et al.
VR research predominantly focuses on upright postures, such as sitting or standing. Recent research has begun exploring VR use while lying down, revealing numerous benefits. However, existing interaction techniques are tailored for upright ...
Investigating 3D Selection Performance While Running in Extended Reality: an In-depth Study of the Effect of Speed [0.03%]
运行速度对扩展现实中的三维选择性能的影响研究:深入探究运行时的速度效应
Ang Li,Jarrod Knibbe,Kiichiro Tatsuzawa et al.
Ang Li et al.
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 multifa...
MitoVis: A Unified Visual Analytics System for End-to-End Neuronal Mitochondria Analysis [0.03%]
MitoVis:统一的神经元线粒体分析端到端可视化分析系统
JunYoung Choi,Hyun-Jic Oh,Hakjun Lee et al.
JunYoung Choi et al.
Neurons have a polarized structure, with dendrites and axons, and compartment-specific functions can be affected by the dwelling mitochondria. Recent studies have shown that the morphology of mitochondria is closely related to the functions...