Computer Vision Lab

Welcome to Computer Vision Lab

We’re looking for strong and motivated graduate students and undergraduate interns.
If you are interested, please apply ►►► HERE.

HandPose

Functional Hand Type Prior for 3D Hand Pose Estimation and Action Recognition from Egocentric View Monocular Videos (Under Review 2023)

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

WWW

Dual Policy Learning for Aggregation Optimization in Recommender Systems (Under Review 2023)

Heesoo Jung, Sangpil Kim, Hogun Park

Soudini

Soundini: Sound-Guided Diffusion for Natural Video Editing (Under Review 2023)

Seunghyun Lee, Sieun Kim, Innfarn Yoo, Feng Yang, Donghyeon Cho, Youngseo Kim, Huiwen Chang, Jinkyu Kim*, Sangpil Kim*

Event Fusion Photometric Stereo Network (Under Review 2023)

Event Fusion Photometric Stereo Network (Under Review 2023)

Wonjeong Ryoo, Giljoo Nam, Jae-Sang Hyun*, Sangpil Kim*

FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment (Under Review 2023)

FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment (Under Review 2023)

Gyeongrok Oh, Heon Gu, Jinkyu Kim*, Sangpil Kim*

Robust Sound-Guided Image Manipulation

Robust Sound-Guided Image Manipulation (Under Review 2023)

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

SMGNN: Self-Supervised Multimodal Graph Neural Network for Recommender Systems

SMGNN: Self-Supervised Multimodal Graph Neural Network for Recommender Systems (Under Review 2022)

Sungjune Kim, Gyusam Chang, Wonseok Roh, Dae-Neung Sohn, Jung-Tae Lee, Hogun Park*, Sangpil Kim*

ORA3D: Overlap Region Aware Multi-view 3D Object Detection

ORA3D: Overlap Region Aware Multi-view 3D Object Detection (BMVC 2022)

Wonseok Roh, Gyusam Chang, Seokha Moon, Giljoo Nam, Chanyoung Kim, Younghyun Kim, Jinkyu Kim*, Sangpil Kim*

Sound-Guided Semantic Video Generation

Sound-Guided Semantic Video Generation (ECCV 2022)

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

Sound-Guided Semantic Image Manipulation

Sound-Guided Semantic Image Manipulation (CVPR 2022)

Seunghyun Lee, Wonseok Roh, Wonmin Byeon, SangHo Yoon, Jinkyu Kim*, Sangpil Kim*

 

The lab challenges unsolved real-life problems by inventing novel artificial intelligence for computer vision. To do so, our research focuses on developing innovative computer vision systems through deep learning algorithms and heterogeneous visual sensors. We also adopt machine learning to innovate visual machine intelligence.

News!
✦ 2023.10. One paper got accepted in Information Sciences(JCR IF Top 10%). Congratulations to all authors!
✦ 2023.08. One paper got accepted in BMVC 2023(Oral). Congratulations to all authors!
✦ 2023.08. One paper got accepted in Neural Networks(JCR IF Top 10%). Congratulations to all authors!
✦ 2023.07. One paper got accepted in ICCV 2023. Congratulations to all authors!
✦ 2023.07. Two paper got accepted in ICML 2023 Workshop. Congratulations to all authors!
✦ 2023.02. One paper got accepted in WWW 2023. Congratulations to all authors!
✦ 2022.09. One paper got accepted in BMVC 2022. Congratulations to all authors!
✦ 2022.07. One paper got accepted in ECCV 2022. Congratulations to all authors!
✦ 2022.03. One paper got accepted in CVPR 2022. Congratulations to all authors!

★ 2023.08. We received GCP Credit Award ($32,600) from Google Research.
★ 2023.05. Seunghyun Lee got an internship offer from Google Research, CA, USA.
★ 2023.05. Gyusam Chang got an internship offer from Samsung AIT(종합기술원).
★ 2022.06. We received Research Funding from Google Research USA.
★ 2023.01. We initiated a collaboration project with Google Research USA.
★ 2022.08. We initiated a collaboration project with Samsung Advanced Institute of Technology.
★ 2022.05. We received GCP Credit Award ($30,000) from Google Research.
★ 2021.09. We initiated a collaboration project with NVIDIA Research USA.

In the narrow scope of research, the lab is interested in the following:
– Multi-modal Generative Model
– Multi-modal Representation Learning
– Domain Generalization and Unsupervised Domain Adaptation
– Computer Vision for Autonomous Driving
– 3D Computer Vision and Inverse Graphics
– Hand Pose Estimation
– Human Computer Interaction
– Diffusion Model

Computer Vision Lab
Department of Artificial Intelligence, Korea University
603, Woojung Hall of Informatics, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841