Gyeongrok Oh

About

I am a Ph.D. student at the department of artificial intelligence in Korea University, supervised by Prof. Sangpil Kim. Previously, I worked as a visiting researcher for one year at Samsung Advanced Institute of Technology (SAIT) in collaboration with the Computer Vision Lab (Advisor: Sujin Jang). My research interests lie at the intersection of computer vision, multi-modal generative models, and embodied AI systems. My work explores how multi-modal generative models can be used to interpret and synthesize complex sensory inputs—such as language, vision, and audio—in unified frameworks. Furthermore, I am particularly interested in developing 3D visual perception techniques and domain adaptation methods that enable embodied AI systems to operate reliably in real-world environments.🚗🤖💬

Topics of Interest

Multi-modal Representaton: Multi-modal generative model. [ ECCV'24, NN'24, CVM'24, ECCV'22 ]
Embodied AI: 3D Visual Perception [ ICML'25, CVPR'25, BMVC'23 ]
Machine Learning: Domain Adaptation, Test-time Adaptation [ ICML'25, AAAI'24 ]

News

[May. 2025] One paper about test-time adaptation is accepted to ICML 2025.🇨🇦
[Feb. 2025] One paper about occupancy prediction is accepted to CVPR 2025.🇺🇸
[Dec. 2024] One paper about video demoire is accepted to Neural Networks.
[July. 2024] One paper about text-to-video generation is accepted to ECCV 2024.🇮🇹
[Mar. 2024] One paper about image manipulation is accepted to Neural Networks.
[Feb. 2024] One paper about image stylization is accepted to Computational Visual Media.
[Jan. 2024] I started research collaboration with Samsung Advanced Institute of Technology.
[Dec. 2023] One paper about domain adaptation for 3DOD is accepted to AAAI 2024.🇺🇸
[Aug. 2023] One paper about hand action recognition is accepted to BMVC 2023 (Oral).🇬🇧
[Sept. 2022] Started the integrated MS/PhD program in the Computer Vision Lab, Korea University.
[July. 2022] One paper about sound-to-video generation is accepted to ECCV 2022.🇮🇱

Publications

Most recent publications on Google Scholar.
* indicates equal contribution.

Selected
All

Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning

Sungjune Kim*, Gyeongrok Oh*, Heeju Ko, Daehyun Ji, Dongwook Lee, Byung-Jun Lee, Sujin Jang, Sangpil Kim

ICML, 2025.

3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation

Gyeongrok Oh*, Sungjune Kim*, Heeju Ko, Hyung-gun Chi, Jinkyu Kim, Dongwook Lee, Daehyun Ji, Sungjoon Choi, Sujin Jang, Sangpil Kim

CVPR, 2025.

Paper Project

FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment

Gyeongrok Oh, Sungjune Kim, Heon Gu, Sang Ho Yoon, Jinkyu Kim*, Sangpil Kim*

Neural Networks, 2024.

Paper Project Code

MEVG: Multi-event Video Generation with Text-to-Video Models

Gyeongrok Oh, Jaehwan Jeong, Sieun Kim, Wonmin Byeon, Jinkyu Kim, Sungwoong Kim, Sangpil Kim

ECCV, 2024.

Paper Project Code

Sound-Guided Semantic Video Generation

Seunghyun Lee, Gyeongrok Oh, Wonmin Byeon, Wonjeong Ryoo, Sang Ho Yoon, Jinkyu Kim*, Sangpil Kim*

ECCV, 2022.

Paper Project Code

LVMark: Robust Watermark for Latent Video Diffusion Models

MinHyuk Jang*, Youngdong Jang*, JaeHyeok Lee, Feng Yang, Gyeongrok Oh, Jongheon Jeong, Sangpil Kim

Pre-print, 2025.

Paper Project

Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning

Sungjune Kim*, Gyeongrok Oh*, Heeju Ko, Daehyun Ji, Dongwook Lee, Byung-Jun Lee, Sujin Jang, Sangpil Kim

ICML, 2025.

3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation

Gyeongrok Oh*, Sungjune Kim*, Heeju Ko, Hyung-gun Chi, Jinkyu Kim, Dongwook Lee, Daehyun Ji, Sungjoon Choi, Sujin Jang, Sangpil Kim

CVPR, 2025.

Paper Project

FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment

Gyeongrok Oh, Sungjune Kim, Heon Gu, Sang Ho Yoon, Jinkyu Kim*, Sangpil Kim*

Neural Networks, 2024.

Paper Project Code

MEVG: Multi-event Video Generation with Text-to-Video Models

Gyeongrok Oh, Jaehwan Jeong, Sieun Kim, Wonmin Byeon, Jinkyu Kim, Sungwoong Kim, Sangpil Kim

ECCV, 2024.

Paper Project Code

Robust Sound-Guided Image Manipulation

Seunghyun Lee*, Hyung-gun Chi*, Gyeongrok Oh, Wonmin Byeon, Sang Ho Yoon, Hyunje Park, Wonjun Cho, Jinkyu Kim, Sangpil Kim

Neural Networks, 2024.

Paper Project

Audio-Guided Implicit Neural Representation for Local Image Stylization

Seung Hyun Lee*, Sieun Kim*, Wonmin Byeon, Gyeongrok Oh, Sumin In, Hyeongcheol Park, Sang Ho Yoon, Sung-hee Hong, Jinkyu Kim, and Sangpil Kim

Computational Visual Media, 2024.

Paper Project

CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-based 3D Object Detection

Gyusam Chang*, Wonseok Roh*, Sujin Jang, Dongwook Lee, Daehyun Ji, Gyeongrok Oh, Jinsun Park, Jinkyu Kim, Sangpil Kim

AAAI, 2024.

Paper Project

Functional Hand Type Prior for 3D Hand Pose Estimation and Action Recognition from Egocentric View Monocular Videos

Wonseok Roh, Seung Hyun Lee, Wonjeong Ryoo, Gyeongrok Oh, Soo Yeon Hwang, Hyung-gun Chi, Sangpil Kim

BMVC (Oral), 2023.

Paper Project Code

Sound-Guided Semantic Video Generation

Seunghyun Lee, Gyeongrok Oh, Wonmin Byeon, Wonjeong Ryoo, Sang Ho Yoon, Jinkyu Kim*, Sangpil Kim*

ECCV, 2022.

Paper Project Code

Education

Korea University

Sept. 2022 - Present

Ph.D. Student in Artificial Intelligence

Inha University

Mar. 2016 - Aug. 2022

B.S. in Computer Science

Vitæ

Full Resume in PDF (Last update: Mar. 2025).

SAIT 2024 - 2025

Visiting Researcher
Computer Vision Lab (Advisor: Sujin Jang)
Korea Univ. 2022 - present

Ph.D. Student
Artificial Intelligence
Inha Univ. 2016 - 2022

B.S. Student
Computer Science

Academic Services

Conference Reviewer

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

2024, 2025

CVF/IEEE International Conference on Computer Vision (ICCV)

2025

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

2023

Program Committee

The Association for the Advancement of Artificial Intelligence (AAAI)

2025