BISPL - Bio Imaging, Signal Processing & Learning Lab.
  • BISPL News
  • Professor
  • Members
  • Research
  • Publications
  • Github
  • Software
    • NIRS-SPM
    • k-t FOCUSS
    • Compressive MUSIC
    • Super-resolution Microscopy
    • Patch Low Rank MRI
    • Sparse SPM
    • ALOHA Inpainting
    • ALOHA for MR Recon
    • MR Artifact Removal using Robust ALOHA
    • MR Ghost Artifact correction using ALOHA
  • Recent Talks
  • COVID-19 data link
  • BISPL Snapshots
  • On the World Press
  • BISPL Hall of Fame
  • Intranet

Latest Research Highlight
CLIPstyler: Image Style Transfer with a Single Text Condition

Gihyun Kwon and Jong Chul Ye, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),  2022. 

See more

Five papers accepted to CVPR 2022!

3/2/2022

 
Congraturations!  Five papers from BISPL are finally accepted for CVPR 2022. The list of the accepted papers is as follows.
  1. Gwanghyun Kim, and Jong Chul Ye. "DiffusionCLIP: Text-guided image manipulation using diffusion models," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  2. Chanyong Jung, Gihyun Kwon, Jong Chul Ye, "Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks",IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  3. Gihyun Kwon, and Jong Chul Ye. "CLIPstyler: Image style transfer with a single text condition,"IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  4. Kwanyoung Kim, Taesung Kwon, and Jong Chul Ye. "Noise distribution adaptive self-supervised image denoising using Tweedie distribution and score matching", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  5. Hyungjin Chung, Byeongsu Sim, and Jong Chul Ye. "Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction",IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

BISPL's new home @ Graduate School of AI

2/9/2022

 
BISPL has joined the Graduate School of AI as of January 3rd, 2022 in order to focus more on the machine learning and artificial intelligence for healthcare.  Accordingly, we are accepting students only through the Graduate School of AI.  For students who are interested in joining BISPL,  please apply to the Graduate School of AI (https://gsai.kaist.ac.kr/admission/​) or contact Prof. Jong Chul Ye.
Picture

"Geometry of Deep Learning" by Prof. Ye made it to BookAuthority's best new Signal Processing books!

1/8/2022

 
Picture

The book is now available for purchase from various online stores

  • Amazon 
  • Springer 
  • WHSmith (UK)
  • Aladin (알라딘, Korea)
  • Google Book

Three papers are accepted for NeurIPS 2021!

9/28/2021

 

  The list of the accepted NeurIPS papers is as follows. Congratulations!

  • Kwanyoung Kim, Jong Chul Ye, "Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Clean Images",  in Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), Virtual, December 2021.
  • Sangjoon Park*, Gwanghyun Kim*, Jeongsol Kim, Boah Kim, Jong Chul Ye, "Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis",  in Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), Virtual, December 2021. (*co-first authors)
  • Byung-Hoon Kim, Jong Chul Ye, Jae-Jin Kim, "Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention",  in Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), Virtual, December 2021.
<<Previous

    BISPL@KAIST

    BISPL is a group of people at KAIST who are eager to dedicate their time and effort to investigate the beauty of bio- and medical imaging with the help of mathematics, machine learning, and physics.
ABOUT US
Our research activities are primarily focused on the signal processing and machine learning  for high-resolution high-sensitivity image reconstruction from real world bio-medical imaging systems. Such problems pose interesting challenges that often lead to investigations of fundamental problems in various branches of physics, mathematics, signal processing, biology, and medicine. While most of the biomedical imaging researchers are interested in addressing this problem using off-the-self tools from signal processing, machine learning, statistics, and optimization and combining their domain-specific knowledge, our approaches are unique in the sense that I believe that actual bio-medical imaging applications are a source of endless inspiration for new mathematical theories and we are eager to solve both specific applications and application-inspired fundamental theoretical problems. 
CONTACT US
Bio Imaging. Signal Processing & Learning
Graduate School of AI
KAIST
291 Daehak-ro, Yuseong-gu
Daejeon 305-701, Korea

Copyright (c) 2014, BISPL
All Rights Reserved.
Picture