Scholar
Hsin-Ying Lee
Google Scholar ID: SeozinYAAAAJ
stealth mode startup
Computer Vision
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
7,394
H-index
33
i10-index
49
Publications
20
Co-authors
8
list available
Contact
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
Publications
7 items
T2Bs: Text-to-Character Blendshapes via Video Generation
2025
Cited
0
UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation
2025
Cited
0
Towards Affordance-Aware Articulation Synthesis for Rigged Objects
2025
Cited
0
DELTA: Dense Efficient Long-range 3D Tracking for any video
arXiv.org · 2024
Cited
1
VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
arXiv.org · 2024
Cited
28
GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement
International Conference on Learning Representations · 2024
Cited
7
Visual Concept-driven Image Generation with Text-to-Image Diffusion Model
arXiv.org · 2024
Cited
4
Resume (English only)
Academic Achievements
- Multiple papers accepted at top conferences such as CVPR, ICLR, NeurIPS, ECCV, ICCV
- 2025: Three papers accepted to CVPR 2025 (one highlight)
- 2025: Four papers accepted to ICLR 2025
- 2024: One paper accepted to NeurIPS 2024
- 2024: One paper accepted to ECCV 2024
- 2024: Five papers accepted to CVPR 2024 (one highlight)
- 2023: One paper accepted to ICLR 2024
- 2023: One paper accepted to SIGGRAPH Asia 2023
- 2023: Two papers accepted to ICCV 2023
- 2023: One paper accepted to ICML 2023
- 2023: Five papers accepted to CVPR 2023 (one highlight)
- 2023: One paper accepted to ICLR 2023 (oral)
- 2022: Three papers accepted to ECCV 2022
- 2022: Two papers accepted to CVPR 2022
- 2022: One paper accepted to ICLR 2022
- 2020: Four papers accepted to ECCV 2020 (one spotlight)
- 2020: Joined Snap Research
- 2019: One paper accepted to ICLR 2020 (spotlight)
- 2019: One paper accepted to IJCV 2019
- 2019: One paper accepted to NeurIPS 2019
- 2019: One paper accepted to ICIP 2019
- 2019: One paper accepted to CVPR 2019
- 2018: Two papers accepted to ECCV 2018 (one oral)
- 2017: One paper accepted to ICCV 2017
Research Experience
- 2020 to 2025: Research Scientist at Snap Research, Creative Vision team
- May 2019: Google Internship, MTV, Audio-Visual Modeling
- December 2018: Google Internship, SNV
- May 2017: Nvidia Internship, Santa Clara, Audio-Visual Modeling
- August 2016: Started PhD at UC Merced
Education
- PhD: University of California, Merced (UC Merced), started in August 2016
Background
- Research Interests: Intersection of AI, 3D, and architectural design
- Professional Field: Computer Vision and Machine Learning, particularly in 2D/3D/4D generation and manipulation
Miscellany
- Email: hsinyinglee.business [at] gmail.com
Co-authors
8 total
Ming-Hsuan Yang
University of California at Merced; Google DeepMind
Co-author 2
Jia-Bin Huang
Capital One Associate Professor at University of Maryland
Yen-Chi Cheng
University of Illinois Urbana-Champaign
Ming-Yu Liu
Vice President of Research at NVIDIA, IEEE Fellow
Ting-Chun Wang
NVIDIA Research
Xiaodong Yang
NVIDIA Research
Chieh Hubert Lin
Somewhere
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up