Taesung Kwon

Bio Imaging, Signal Processing & Learning Lab (BISPL), KAIST AI.

About Me

Hi, my name’s Taesung and I’m a fourth-year Ph.D. candidate in KAIST, advised by Prof. Jong Chul Ye and Prof. Mooseok Jang. My research focuses on computer vision (CV) and its intersection with generative models, exploring their applications in solving inverse problems and enhancing image and video processing. My recent research aims to improve the conditional generative process by controlling the diffusion generative process. Additionally, I explore methods to leverage temporal correlations to improve the performance of inverse problem solvers.

My research spans three key areas:

  • Generative Models: Diffusion models for video inverse problems, video frame interpolation, and image editing.

  • Low-Level Vision: Unsupervised/self-supervised denoising methods for images and videos.

  • Physics-Based Vision and Medical Imaging: Applications to physical sciences (e.g., inverse scattering in optics) and medical imaging.

Education

KAIST

Ph.D. Candidate in Bio and Brain Engineering

Advisors: Jong Chul Ye and Mooseok Jang

2022 - Current

KAIST

M.S. in Bio and Brain Engineering

Advisor: Jong Chul Ye

2020 - 2022

KAIST

B.S. in Bio and Brain Engineering

Advisor: Yoonkey Nam

2015 - 2020

Research

VISION-XL: High Definition Video Inverse Problem Solver using Latent Diffusion Models

https://vision-xl.github.io/

Taesung Kwon, J. C. Ye

arXiv, 2024

Solving HD video inverse problems using only latent diffusion models. Supporting wide-range ratio using SDXL.

ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler

https://vibidsampler.github.io/

S. Yang*, Taesung Kwon*, J. C. Ye (*co-first)

ICLR 2025

State-of-the-art performance, efficiently generating high-quality, smooth videos between keyframes.

Solving Video Inverse Problems Using Image Diffusion Models

https://svi-diffusion.github.io/

Taesung Kwon, J. C. Ye

ICLR 2025

Solving video inverse problems using only image diffusion models, with batch-consistent sampling stretagy.

Video Reconstruction Beyond Dynamic Scattering Medium

https://github.com/star-kwon/VDPS

Taesung Kwon*, G. Song*, Y. Kim, J. Kim, J. C. Ye, M. Jang (*co-first)

Submitted to TPAMI

Video reconstruction through dynamic scattering layer using video diffusion models.

Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion

https://hiper0.github.io/

I. Han*, S. Yang*, Taesung Kwon, J. C. Ye

arXiv, 2023

Image manipulation using personalized text embedding from Stable Diffusion.

DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation

https://github.com/gwang-kim/DiffusionCLIP

G. Kim, Taesung Kwon, J. C. Ye

CVPR, 2022

Robust text-driven image manipulation using text-to-image diffusion models.

Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matching

https://github.com/cubeyoung/NoiseAdaptive2Score

K. Kim, Taesung Kwon, J. C. Ye

CVPR, 2022

Noise distribution and level adaptive denoising framework using Tweedie distribution and score matching.

Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoising

https://github.com/star-kwon/TCI_CyclefreeCycleGAN

Taesung Kwon, J. C. Ye

IEEE TCI, 2021

Efficient CycleGAN framework for low-dose CT denoising.

Workshop

NTIRE 2022 Spectral Recovery Challenge and Data Set

CVPRW, 2022

Recovering hyperspectral information from JPEG-compressed RGB images.

NTIRE 2022 Challenge on Night Photography Rendering

CVPRW, 2022

Recovering the visual appearance of night photography.

Patents

  • Method and Apparatus for Low-Dose X-Ray Computed Tomography Image Processing Based on Efficient Unsupervised Learning Using Invertible Neural Network

J. C. Ye, Taesung Kwon

U.S. Patent Application, Filed, No. 17/848,689, 2022

Korean Patent, Granted, No. 10-2643601, 2024

Awards and Honors

  • KAIST Scholarship, KAIST, 2022-2025
  • Korean Government Scholarship, KAIST, 2020-2021

Services

  • Conference reviewers: CVPR, ICLR, ECCV, ICML
  • Journal reviewers: IEEE Transactions on Computational Imaging
  • Lab Manager, BISPL, 2024