Hsin-Ying Lee

Snap (United States) — United States

Computer Science · Physical Sciences

25h-index4.3kcitations83works8.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Generative Adversarial Networks and Image Synthesis(36), Advanced Vision and Imaging(18), Computer Graphics and Visualization Techniques(16), Multimodal Machine Learning Applications(16), Advanced Image and Video Retrieval Techniques(11)

Publications82 total

Visual Concept-driven Image Generation with Text-to-Image Diffusion Model
2025· 3 citedOpen Access
Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
2024· 45 cited
3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting
arXiv (Cornell University)·2024· 1 citedOpen Access
Prediction of In-Hospital Cardiac Arrest in the Intensive Care Unit: Machine Learning–Based Multimodal Approach
JMIR Medical Informatics·2024· 16 citedOpen Access
Visual Concept-driven Image Generation with Text-to-Image Diffusion Model
arXiv (Cornell University)·2024Open Access
AToM: Amortized Text-to-Mesh using 2D Diffusion
arXiv (Cornell University)·2024Open Access
Diffusion Priors for Dynamic View Synthesis from Monocular Videos
arXiv (Cornell University)·2024Open Access
ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes
2024· 7 cited
Upper Extremity Reconstruction Post-Tumor Resection: Innovations and Challenges in Limb Preservation for Advanced-Stage Malignant Giant Cell Tumor of Bone
International Microsurgery Journal·2024Open Access
SceneWiz3D: Towards Text-guided 3D Scene Composition
arXiv (Cornell University)·2023· 2 citedOpen Access
UpFusion: Novel View Diffusion from Unposed Sparse View Observations
arXiv (Cornell University)·2023Open Access
Exploiting Diffusion Prior for Generalizable Dense Prediction
arXiv (Cornell University)·2023Open Access
SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors
arXiv (Cornell University)·2023· 2 citedOpen Access
Text2Tex: Text-driven Texture Synthesis via Diffusion Models
2023· 121 cited
InfiniCity: Infinite-Scale City Synthesis
2023· 33 cited
Text-Guided Synthesis of Eulerian Cinemagraphs
arXiv (Cornell University)·2023· 1 citedOpen Access
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
arXiv (Cornell University)·2023· 75 citedOpen Access
3DAvatarGAN: Bridging Domains for Personalized Editable Avatars
2023· 29 cited
DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis
2023· 40 cited
Machine Learning-Based Multimodal Prediction of In-Hospital Cardiac Arrest in the ICU (Preprint)
2023Open Access
page 1 of 5Next →

Frequent Co-authors

Ming–Hsuan Yang(27), Hung-Yu Tseng(18), Jia‐Bin Huang(10), Sergey Tulyakov(9), Maneesh Singh(5), Yu-Ding Lu(5), Aliaksandr Siarohin(5), Winston H. Hsu(5), Qi Mao(4), Lu Jiang(4), Weilong Yang(4), Peter Wonka(4), Menglei Chai(4), Kyle Olszewski(4), Siwei Ma(3), Shin-I Cheng(3), Yujie Chen(3), Wei-Chen Chiu(3), Yan-Bo Lin(3), Yen‐Yu Lin(3)