Siyu Zhu

Shanghai Jiao Tong University — China

Computer Science · Physical Sciences

22h-index2.9kcitations81works2.92yr 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(35), Robotics and Sensor-Based Localization(24), Advanced Image and Video Retrieval Techniques(18), 3D Surveying and Cultural Heritage(9), Computer Graphics and Visualization Techniques(8)

Publications81 total

PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image
arXiv (Cornell University)·2025Open Access
Pyramidal Patchification Flow for Visual Generation
arXiv (Cornell University)·2025Open Access
DicFace: Dirichlet-Constrained Variational Codebook Learning for Temporally Coherent Video Face Restoration
arXiv (Cornell University)·2025Open Access
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
2025· 7 cited
4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 4 citedOpen Access
A Lightweight TA-YOLOv8 Method for the Spot Weld Surface Anomaly Detection of Body in White
Applied Sciences·2025· 3 citedOpen Access
Three-Parameter Adaptive k-Nearest Neighbors Algorithm Based on Maximum Fuzzy Probability Criterion
SSRN Electronic Journal·2025Open Access
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
arXiv (Cornell University)·2024Open Access
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
Lecture notes in computer science·2024· 36 cited
Freditor: High-Fidelity and Transferable NeRF Editing by Frequency Decomposition
Lecture notes in computer science·2024· 3 cited
Classifying extended, localized and critical states in quasiperiodic lattices via unsupervised learning
Chinese Physics B·2024
Classifying extended, localized and critical states in quasiperiodic lattices via unsupervised learning
arXiv (Cornell University)·2024Open Access
Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
arXiv (Cornell University)·2024· 3 citedOpen Access
AlphaFolding: 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance
arXiv (Cornell University)·2024Open Access
EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head
arXiv (Cornell University)·2024Open Access
Freditor: High-Fidelity and Transferable NeRF Editing by Frequency Decomposition
arXiv (Cornell University)·2024Open Access
Image inpainting for ECEI based on DeepFillv2 model
Fusion Engineering and Design·2024· 4 cited
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
arXiv (Cornell University)·2024· 1 citedOpen Access
VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model
arXiv (Cornell University)·2024· 1 citedOpen Access
Text-Video Retrieval Re-Ranking Via Multi-Grained Cross Attention and Frozen Image Encoders
SSRN Electronic Journal·2024· 1 citedOpen Access
page 1 of 5Next →

Frequent Co-authors

Ping Tan(20), Long Quan(15), Tian Fang(13), Tianwei Shen(10), Runze Zhang(10), Lei Zhou(7), Zuozhuo Dai(6), Weihao Yuan(6), Chengzhou Tang(5), Xiaodong Gu(4), Zhiwen Fan(4), Feitong Tan(4), Zixin Luo(4), Richard Zanibbi(4), Jinglu Wang(4), Zilong Dong(4), Chiew‐Lan Tai(3), Rui Huang(3), Qingkun Su(3), Xiaodong Gu(2)