Scholar
Luchuan Song
Google Scholar ID: UVsyxOoAAAAJ
University of Rochester
Citations & Impact
Citations
825
H-index
14
i10-index
18
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- - StreamME: Simplify 3D Gaussian Avatar within Live Stream (Siggraph 2025)
- - Free-viewpoint Human Animation with Pose-correlated Reference Selection (CVPR 2025, Highlight)
- - TextToon: Real-Time Text Toonify Head Avatar from Single Video (Siggraph Asia 2024)
- - Tri2-plane: Thinking Head Avatar via Feature Pyramid (ECCV 2024)
- - Adaptive Super Resolution for One-Shot Talking Head Generation (ICASSP 2024)
- - EAGLE: Egocentric AGgregated Language-video Engine (ACM'MM 2024)
- - IDRNet: Intervention-driven relation network for semantic segmentation (NeurIPS 2023)
- - Video understanding with large language models: A survey (Arxiv 2023)
Research Experience
- Interned at Adobe Research, working with Dr. Yang Zhou. Involved in multiple research projects including StreamME, Free-viewpoint Human Animation with Pose-correlated Reference Selection, TextToon, Tri2-plane, Adaptive Super Resolution for One-Shot Talking Head Generation, EAGLE, and IDRNet.
Education
- Ph.D.: University of Rochester, Advisor: Prof. Chenliang Xu; Master and Bachelor: University of Science and Technology of China, Advisors: Prof. Nenghai Yu and Prof. Bin Liu.
Background
- Research Interests: Face animation and stylization, 3D face reconstruction, deepfake detection, egocentric video understanding, object detection/segmentation, and optical character recognition (OCR). Personal Background: Currently a third-year Ph.D. student in the Computer Science Department at the University of Rochester.
Miscellany
- Hobbies: Mountaineering, summited Muztagh Ata and Chola mountains.
