
I am a researcher passionate about computer vision and machine learning. I received my bachelor’s degree (Summa Cum Laude) in Computer Science and Engineering at POSTECH, where I was fortunate to work with Prof. Tae-Hyun Oh and Prof. Suha Kwak. During my undergraduate, I also studied at Stanford, UIUC and UC Berkeley.
The goal of my research is to build human-like embodied agents that perceive, reason about, and interact with our dynamic 3D world. To this end, I focus on (i) 3D/4D reconstruction of humans, objects, and scenes, (ii) spatial and semantic reasoning over human-object-scene compositions, and (iii) generation of object/scene-aware 4D human behaviors. I have published first-authored papers at CVPR, ECCV and ICCV, and been recognized as an outstanding reviewer at ICCV 2023.
News
02/2025 | Our paper on 3D shape reconstruction, ZeroShape-W, is accepted to CVPR 2025. |
---|---|
06/2024 | I am attending CVPR 2024 in person. Looking forward to seeing you in Seattle! |
10/2023 | I am selected as an outstanding reviewer (top 1.89%) at ICCV 2023. |
10/2023 | I am attending ICCV 2023 in person. Looking forward to seeing you in Paris! |
07/2023 | Our paper on domain generalization, PromptStyler, is accepted to ICCV 2023. |
10/2022 | I am attending ECCV 2022 in person. Looking forward to seeing you in Tel Aviv! |
07/2022 | Our paper on 3D human reconstruction, FastMETRO, is accepted to ECCV 2022. |
03/2022 | Our paper on situation recognition, CoFormer, is accepted to CVPR 2022. |
01/2022 | I won the best research project award from POSTECH CSE. |
10/2021 | Our paper on situation recognition, GSRTR, is accepted to BMVC 2021. |
01/2021 | I won the minister’s award from Ministry of Science and ICT. |
Selected Publications
-
Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the WildIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
-
PromptStyler: Prompt-driven Style Generation for Source-free Domain GeneralizationIEEE/CVF International Conference on Computer Vision (ICCV), 2023
-
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with TransformersEuropean Conference on Computer Vision (ECCV), 2022
-
Collaborative Transformers for Grounded Situation RecognitionIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Honors and Awards
ICCV Outstanding Reviewer (2023), IEEE/CVF International Conference on Computer Vision
|
Professional Services
Conference Reviewer
|