Seoyoung Lee

I am a Ph.D. student at The University of Texas at Austin, advised by Prof. Atlas Wang at VITA Group. My research interest lies in task-aware embodied AI systems that connect 3D scene understanding and reconstruction with downstream decision-making, with the goal of enabling reliable and safety-aware autonomy in complex real-world environments.

Previously, I was at Visual Information Processing Lab, Seoul National University (SNU) where I completed my master's studies with Prof. Joonseok Lee, studying computer vision. Before that, I received Bachelor's degrees in Statistics and Business Administration at SNU, where I worked with Prof. Taesung Park and Prof. Iksoo Huh on statistical meta-analysis at Bioinformatics and Biostatistics Lab.

My first name is pronounced "Suh-young (서영)" []

profile photo
NVIDIA Adobe UT Austin Seoul National University
News
Research
Seeing Where to Deploy: Metric RGB-Based Traversability Analysis for Aerial-to-Ground Hidden Space Inspection
Seoyoung Lee, Shaekh Mohammad Shithil, Durgakant Pushp, Lantao Liu, Zhangyang Wang
IROS, 2026
project page / paper / video
CIPHER: Culvert Inspection through Pairwise Frame Selection and High-Efficiency Reconstruction
Seoyoung Lee, Zhangyang Wang
ICCVW E2E3D, 2025
paper
Joint Object Detection and Sound Source Separation
Sunyoo Kim, Yunjeong Choi, Doyeon Lee, Seoyoung Lee, Eunyi Lyoo, Seungju Kim, Junhyug Noh, Joonseok Lee
ISMIR, 2025
paper
Expressive Gaussian Human Avatars from Monocular RGB Video
Hezhen Hu, Zhiwen Fan, Tianhao Wu, Yihan Xi, Seoyoung Lee, Georgios Pavlakos, Zhangyang Wang
NeurIPS, 2024
project page / paper / code
PoseDiff: Pose-conditioned Diffusion Model for Unbounded Scene Synthesis from Sparse Inputs
Seoyoung Lee, Joonseok Lee
WACV, 2024
paper
Disentangled Audio-Driven NeRF: Talking Head Generation with Detailed Identity-Specific Micro expressions
Seoyoung Lee*, Seongsu Ha*, Joonseok Lee
CVPR Workshops: Sight and Sound, 2023
paper
Learning to Wear: Details-Preserved Virtual Try-on via Disentangling Clothes and Wearer
Sangho Lee, Seoyoung Lee, Joonseok Lee
BMVC, 2022
project page / paper
Towards Efficient Neural Scene Graphs by Learning Consistency Fields
Yeji Song, Chaerin Kong, Seoyoung Lee, Nojun Kwak, Joonseok Lee
BMVC, 2022
project page / paper / code
Towards Detailed Characteristic-Preserving Virtual Try-On
Sangho Lee*, Seoyoung Lee*, Joonseok Lee
CVPR Workshops: The 5th Workshop on Computer Vision for Fashion, Art, and Design, 2022   (Oral Presentation)
paper / video
Meta-Analysis of Randomized Clinical Trials Evaluating Effectiveness of a Multivitamin Supplementation against Oxidative Stress in Healthy Subjects
Seoyoung Lee*, Iksoo Huh*, Seunghee Kang, Yea-eun Nam, Youngseo Cho, Md Kamruzzaman, Jina Hong, Oran Kwon, Taesung Park
Nutrients, 2022   (Issue Cover)
paper

Source code credit to Dr. Jon Barron