Let there be LAIT!
"Together, we transform IMAGINATIONs into REALITY"
We believe in challenging the limits of how we see and understand the world. We believe that a good algorithm must be explainable by a set of simple and concrete principles.
The way we challenge the limits is by building a strong and intelligent model that can recreate the world we perceive. With the help of signal processing and machine learning, we develop an algorithm that analyzes and synthesizes millions of images, audios, and videos to acquire "world models." Along the way, the models we learn provide insights that help us seek mathematical elegance and a clear understanding of our world. This, in turn, motivates us to find better ways to model signals in nature.
We publish our work in major medical imaging / signal processing journals as well as in major machine learning / computer vision conferences.
[2024.04] Our paper "Universal Dehazing via Haze Style Transfer" has been accepted to IEEE TCSVT !
[2024.02] I will serve as an Award Committee of ICASSP 2024.
[2024.02] Congratulation! Our students received Best Paper Awards (one Gold & two Bronze) and four Best Poster Awards from IPIU2024 !
[2024.01] Congratulation! Our paper "STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models" has been accepted to ICLR 2024!
[2024.01] Congratulation! Our paper "Data Augmentation for Low-Level Vision: CutBlur and Mixture-of-Augmentation" has been accepted to Springer International Journal of Computer Vision (Impact Factor 19.5)!
[2023.11] Congratulation! Our paper "Bridging the Domain Gap: A Simple Domain Matching Method for Reference-based Image Super-Resolution in Remote Sensing" has been accepted to IEEE GRSL!
[2023.10] Congratulation! Our paper "RADIO: Reference-Agnostic Dubbing Video Synthesis" has been accepted to WACV 2024!
[2023.09] Congratulation! Our paper "TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models" has been accepted to NeurIPS 2023!
[2023.06] Congratulation! Sanghun and Hyeonjin have won the second place in CVPR 2023 Workshop on Multimodal Learning for Earth and Environment (MultiEarth 2023)!
[2023.06] Congratulation! Wooseok has been accepted into NAVER's internship program!
[2023.06] Congratulation! Jeongho has been accepted into SIA's internship program!
[2023.06] Congratulation! Yejun has been accepted into LISER's research exchange program at Luxembourg!
[2023.02] Congratulation! Two papers (LANIT, Fix the Noise) have been accepted to CVPR 2023!
[Wanted] I am looking for strong and motivated students (or interns). The partial list of future project topics are as follows:
Solving various inverse problems (e.g, super-resolution, image compression, medical image reconstruction, etc.)
Self-supervised representation learning
Generative models and evaluation metrics
Students who are interested in those topics, please check Announcements.
Selected Papers
For an entire publication list, please check my Google Scholar
TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models
Pumjun Kim, Yoojin Jang, Jisu Kim, Jaejun Yoo
NeurIPS 2023 (Corresponding author)
Paper | Code | Project page
Can We Find Strong Lottery Tickets in Generative Models?
Sangyeop Yeo, Yoojin Jang, Jy-yong Sohn, Dongyoon Han, Jaejun Yoo
AAAI 2023 (Corresponding author)
Rethinking the Truly Unsupervised Image-to-Image Translation
Kyungjune Baek, Yunjey Choi, Youngjung Uh, Jaejun Yoo, Hyunjung Shim
ICCV 2021 (Research Mentor)
Time-Dependent Deep Image Prior for Dynamic MRI
Jaejun Yoo, Kyong Hwan Jin, Harshit Gupta, Jerome Yerly, Matthias Stuber, Michael Unser
IEEE TMI (JCR: Journal Citation Reports IF rank upper 10%) 2021 (First author)
Reliable Fidelity and Diversity Metrics for Generative Models
Muhammad Ferjad Naeem*, Seong Joon Oh*, Youngjung Uh, Yunjey Choi, Jaejun Yoo
ICML 2020 (Corresponding author)
Paper | Code | Video (En) | Video (Kr)
Photorealistic Style Transfer via Wavelet Transforms
Jaejun Yoo*, Youngjung Uh*, Sanghyuk Chun*, Byeongkyu Kang, and Jung-Woo Ha
ICCV 2019 (Co-first author)
Paper | Code | Video (En) | Video (Kr)
Selected Talks
Image Enhancement Techniques: CutBlur, WCT2, and SimUSR
CVPR 2020 (Naver LABS)
신호처리 이론으로 실용적인 스타일 변환 모델 만들기 (Better Faster Stronger Transfer)
Deview 2019