Yonghan Lee

University of Maryland, College Park — United States

Computer Science · Physical Sciences

7h-index122citations37works0.92yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Advanced Vision and Imaging(11), Robotics and Sensor-Based Localization(7), Speech and Audio Processing(6), Speech Recognition and Synthesis(5), 3D Surveying and Cultural Heritage(4)

Publications37 total

TK-Planes: Tiered K-Planes with High Dimensional Feature Vectors for Dynamic UAV-based Scenes
2025
MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency
arXiv (Cornell University)·2025Open Access
RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization
arXiv (Cornell University)·2025Open Access
EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching
2025
UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splatting
arXiv (Cornell University)·2025Open Access
UAVTwin: Neural Digital Twins for UAVs using Gaussian Splatting
arXiv (Cornell University)·2025Open Access
IM360: Large-scale Indoor Mapping with 360 Cameras
arXiv (Cornell University)·2025Open Access
MeshGS: Adaptive Mesh-Aligned Gaussian Splatting for High-Quality Rendering
Lecture notes in computer science·2024· 9 cited
MeshGS: Adaptive Mesh-Aligned Gaussian Splatting for High-Quality Rendering
arXiv (Cornell University)·2024Open Access
Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering
arXiv (Cornell University)·2024· 1 citedOpen Access
LEARNING-BASED PERSONAL SPEECH ENHANCEMENT FOR TELECONFERENCING BY EXPLOITING SPATIAL-SPECTRAL FEATURES
IEEE RESOURCE CENTERS·2024Open Access
TK-Planes: Tiered K-Planes with High Dimensional Feature Vectors for Dynamic UAV-based Scenes
arXiv (Cornell University)·2024· 1 citedOpen Access
Array configuration-agnostic personalized speech enhancement using long-short-term spatial coherence
The Journal of the Acoustical Society of America·2023· 2 cited
Array Configuration-Agnostic Personalized Speech Enhancement using Long-Short-Term Spatial Coherence
arXiv (Cornell University)·2022Open Access
Multi-channel target speech enhancement based on ERB-scaled spatial coherence features
arXiv (Cornell University)·2022· 1 citedOpen Access
SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning
2022 International Conference on Robotics and Automation (ICRA)·2022· 4 cited
Learning-Based Personal Speech Enhancement for Teleconferencing by Exploiting Spatial-Spectral Features
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)·2022· 7 cited
A Single Correspondence Is Enough: Robust Global Registration to Avoid\n Degeneracy in Urban Environments
arXiv (Cornell University)·2022Open Access
SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning
arXiv (Cornell University)·2022Open Access
Learning-based personal speech enhancement for teleconferencing by exploiting spatial-spectral features
arXiv (Cornell University)·2021· 1 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Dinesh Manocha(17), Dongki Jung(13), Jaehoon Choi(9), Heesung Kwon(7), Deok-Hwa Kim(7), Yicheng Hsu(6), Mingsian R. Bai(6), Hyungtae Lee(4), Jaehoon Choi(4), Suyong Yeon(4), Jaehoon Choi(4), Sun‐Kyu Lee(3), Donghwan Lee(3), Soohyun Ryu(3), Christopher Maxey(3), Sungmin Eum(3), Dongjun Lee(2), Yeokwon Yoon(2), Yeon‐Hee Lim(2), Hyun‐Suk Kim(2)