Xiaoyang Lyu

University of Hong Kong — Hong Kong

Computer Science · Physical Sciences

10h-index650citations32works8.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(18), 3D Shape Modeling and Analysis(10), Computer Graphics and Visualization Techniques(7), Advanced Image Processing Techniques(6), Robotics and Sensor-Based Localization(5)

Publications32 total

EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes
arXiv (Cornell University)·2025Open Access
UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction
arXiv (Cornell University)·2025Open Access
Deformable Radial Kernel Splatting
2025· 1 cited
MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction
arXiv (Cornell University)·2025Open Access
Deformable Radial Kernel Splatting
arXiv (Cornell University)·2024Open Access
How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach
arXiv (Cornell University)·2024· 1 citedOpen Access
Splatter a Video: Video Gaussian Representation for Versatile Processing
arXiv (Cornell University)·2024Open Access
EscherNet: A Generative Model for Scalable View Synthesis
2024· 18 cited
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
2024· 91 cited
Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction
2024· 3 cited
3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splatting
arXiv (Cornell University)·2024· 1 citedOpen Access
Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction
arXiv (Cornell University)·2024Open Access
DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos
arXiv (Cornell University)·2024Open Access
Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting
arXiv (Cornell University)·2024· 7 citedOpen Access
EscherNet: A Generative Model for Scalable View Synthesis
arXiv (Cornell University)·2024· 2 citedOpen Access
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
arXiv (Cornell University)·2023· 4 citedOpen Access
Learning A Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation
2023· 13 cited
Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video
2023· 9 cited
RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction
2023· 11 cited
Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video
arXiv (Cornell University)·2023Open Access
page 1 of 2Next →

Frequent Co-authors

Xiaojuan Qi(20), Yong Liu(8), Yang-Tian Sun(7), Yan‐Pei Cao(7), Mengmeng Wang(6), Lina Liu(6), Xibin Song(4), Liangjun Zhang(4), Yihua Huang(4), Peng Dai(4), Dongyu Yan(4), Ziyi Yang(4), Junwei Diao(3), Zizhang Li(3), Yi Lin(3), Xiuzhe Wu(3), Ying Shan(3), Chirui Chang(3), Xin Kong(2), Xinxin Chen(2)