About

I am a Ph.D. student at VILAB, advised by Prof. Tae Hyun Kim, working on generative models for low-level vision. My research focuses on dehazing and shadow removal.

I received my B.S. in Mathematics from Hanyang University, and I now leverage this background in Bayesian methods and generative models for low-level vision.

News

[07, 2025] One paper is accepted to ICCV 2025!

[10, 2023] One paper is accepted to CIKM 2023!

Publications

Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing

Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing

Authors: Junseong Shin*, Seungwoo Chung*, Yunjeong Yang, Tae Hyun Kim

ICCV 2025

Code Paper Project Page
Dehazing Rectified Flow Markov Chain Brownian Motion
PAPP: Plug-And-Play Prompts for Shadow Removal

PAPP: Plug-And-Play Prompts for Shadow Removal

Authors: Junseong Shin*, Seungwoo Chung*, Tae Hyun Kim

Under review

Code

Shadow Removal Prompt Learning Plug-and-play
Deep Variational Bayesian Modeling of Haze Degradation Process

Deep Variational Bayesian Modeling of Haze Degradation Process

Authors: Eun Woo Im*, Junseong Shin*, Sungyong Baik, Tae Hyun Kim

CIKM 2023

Code Paper
Dehazing Variational Inference Bayesian Plug-and-play

Contact

Email is the best way to reach me: junsung6140@hanyang.ac.kr