Welcome!

Digital Image Media Lab. was founded at Yonsei University in 1996. Under supervision of
Prof. Kwanghoon Sohn, various topics in digital image processing field have been researched.

Specific topics we are interested in and researching currently are:

3D Video Processing Deep Learning for 3D Video Processing Multi-view Video Processing Image Enhancement / Editing Intelligent Computer Vision Deep Learning for Vision ADAS(advanced driver assistance systems) Multispectral Imaging / Feature Extraction

News

Congratulations! Seungryong Kim(Ph.D. Student)'s paper has been accepted in ICCV (Oral), Oct. 2017

"DCTM: Discrete-Continuous Transform Matching for Semantic Flow"
S. Kim, D. Min, S. Lin, and K. Sohn
International Conference on Computer Vision(ICCV), Oct 2017.


Congratulations! 8 members' papers have been accepted in ICIP, Sep. 2017

"Pedestrian Proposal Generation using Depth-aware Scale Estimation"
K. Park, S. Kim and K. Sohn
"Deep Stereo Confidence Prediction for Depth Estimation"
S. Kim, D. Min, B. Ham, S. Kim and K. Sohn
"Depth Prediction from a Single Image with Conditional Adversarial Networks"
H. Jung, Y. Kim, D. Min, C. Oh and K. Sohn
"Multi-spectral Human Co-segmentation via Joint Convolutional Neural Networks"
S. Choi, S. Kim, K. Park and K. Sohn
"Automatic 2D-to-3D Conversion using Multi-scale Deep Neural Network"
J. Lee, H. Jung, Y. Kim and K. Sohn
"Unsupervised Stereo Matching using Correspondence Consistency"
S. Joung, S. Kim, B. Ham and K. Sohn
"Convolutional Feature Pyramid Fusion via Attention Network"
S. Jeon, S. Kim and K. Sohn
"Convolutional Cost Aggregation for Robust Stereo Matching"
S. Jeong, S. Kim, B. Ham and K. Sohn
IEEE International Conference on Image Processing(ICIP), Sep 2017.


Congratulations! Youngjung Kim(Ph.D. Student)'s paper has been accepted for publication in IEEE Trans. on Image Processing, May. 2017

"Fast Domain Decomposition for Global Image Smoothing"
Y. Kim, D. Min, B. Ham, and K. Sohn
IEEE Trans. on Image Processing, May 2016.


An article about collaboration between MSRA and DIML is published on the Microsoft Webpage, May. 2017

Link to article
"Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields"
S. Kim, K. Park, K. Sohn, and S. Lin
in Proc. European Conference on Computer Vision(ECCV), Oct 2016.


Congratulations! Youngjung Kim(Ph.D. Student)'s paper has been accepted in CVPR (spotlight), Mar. 2017

"Deeply Aggregated Alternating Minimization for Image Resotration."
Y. Kim, H. Jung, D. Min, and K. Sohn
IEEE Conf. Computer Vision Pattern Recognition(CVPR), Mar 2017.


Congratulations! Seungryong Kim(Ph.D. Student)'s paper has been accepted in CVPR, Mar. 2017

"FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence."
S. Kim, D. Min, B. Ham, S. Jeon, S.Lin and K. Sohn
IEEE Conf. Computer Vision Pattern Recognition(CVPR), Mar 2017.


Congratulations! Jongin Son(Ph.D.) and Hangil Choi(M.S.) have been graduated from Yonsei Univ. Feb. 2017
Congratulations! Seungryong Kim(Ph.D. Student)'s paper has been accepted for publication in IEEE Trans. on Image Processing, Nov. 2016

"Modality-Invariant Image Classification Based on Modality Uniqueness and Dictionary Learning."
S. Kim, R. Cai, K. Park, S. Kim, and K. Sohn
IEEE Trans. on Image Processing, November 2016.


Congratulations! Seungryong Kim(Ph.D. Student)'s paper has been accepted for publication in IEEE Trans. on Pattern Analysis and Machine Intelligence, Sep. 2016

"DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence Estimation."
S. Kim, D. Min, B. Ham, M. Do, and K. Sohn
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), September 2016.


Congratulations! Seungryong Kim(Ph.D. Student), Kihong Park(Ph.D. Student) and Hangil Choi(M.S. Student) won the Hyundai Hackathon Callenge 2016, Aug. 2016



"딥러닝을 이용한 실시간 트래픽 모니터링 시스템"
S. Kim, K. Park, and H. Choi
Hyundai Hackathon Callenge 2016


Congratulations! Seungchul Ryu(Ph.D. Student)'s paper has been accepted for publication in Pattern Recognition, Sep. 2016

"Local Area Transform for Cross Modal Correspondence Matching."
S. Ryu, S. Kim, and K. Sohn
Pattern Recognition (PR), September 2016.


Congratulations! Youngjung Kim(Ph.D. Student)'s paper has been accepted for publication in IEEE Trans. on Image Processing, Aug. 2016

"Structure selective depth super-resolution for RGB-D cameras."
Y. Kim, B. Ham, C. Oh, and K. Sohn
IEEE Trans. on Image Processing, August 2016.


• Congratulations! Bumsub Ham(Ph.D.) will join the faculty of Yonsei University, Aug. 2016
• Congratulations! Seungryong Kim(Ph.D. Student)'s papers have been accepted in ECCV (spotlight), Jul. 2016

Recent activities

• CVPR 2017, Hawaii, US: Y. Kim, "Deeply Aggregated Alternating Minimization for Image Resotration"
• CVPR 2017, Hawaii, US: K. Kim, "FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence"
• ICCE 2017, Las Vegas, US: K. Kim, "Lazy Dragging: Effortless Bounding-box Drawing for Touch-screen Devices"
• APSIPA 2016, Jeju, KOR: K. Park, "Homography Flow for Dense Correspondences"
• ICPR 2016, Cancun, MEX: H. Choi, "Multi-spectral Pedestrian Detection Based on Accumulated Object Proposal with Fully Convolution Network"
• ACCV 2016, Taipei, TPE: C. Oh, "Point-cut: Interactive Image Segmentation using One-point Supervision"
• ECCV 2016, Amsterdam, NLD: S. Kim, "Deep Self-Convolutional Activations Descriptor for Dense Cross-Modal Correspondence"
• ECCV 2016, Amsterdam, NLD: S. Kim, "Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields"
• ICIP 2016, Arizona, US: S. Kim, "ANCC FLOW: Adaptive Normalized Cross-Correlation with Evolving Guidance Aggregation for Dense Correspondence Estimation"
• EI 2016, San Francisco, US: S. Choi, "Multi-level segment based dense correspondence: an affine transformation approach"
• EI 2016, San Francisco, US: H. Jeong, "Depth Extraction from a Single Image Based on Block-Matching and Robust Regression"
• ICCE 2016, Las Vegas, US: K. Kim, "Non-Parametric Human Segmentation Using Support Vector Machine"
• ICCVE 2015, Shenzhen, CHI: J. Seo, "Segment-based Free Space Estimation using Plane Normal Vector in Disparity Space"
• ICIP 2015, Quebec, CAN: C. Oh, "Sparse Edit Propagation for High Resolution Image using Support Vector Machines"
• ICIP 2015, Quebec, CAN: Y. Kim, "A Majorize-minimize Approach for High-Quality Depth Upsampling"
• ICIP 2015, Quebec, CAN: S. Kim, "Learning Depth From a Single Image Using Visual-Depth Words"
• ICIP 2015, Quebec, CAN: J. Son, "Fast Affine-invariant Image Matching Based on Global Bhattacharyya Measure with Adaptive Tree"
• BMVC 2015, Swansea, UK: K. Kim, "Real-time Human Detection based on Personness Estimation"
• BMVC 2015, Swansea, UK: K. Park, "Randomized Global Transformation Approach for Dense Correspondence"
• CVPR 2015, Boston, US: S. Kim, "DASC: Dense Adaptive Self-Correlation Descriptor for Multi-modal and Multi-spectral Correspondence"

 

Menu

• Home
• Introduction
• Research
  • Overview
    
  • Projects
• People
  • Professor
    
  • Research Professor
  • Students
  • Alumni
• Lecture
  • Undergraduate
    
  • Graduate
  • Graduate (Engineering)
• Publications
  • International Journals
    
  • International Conferences
  • Domestic Journals
  • Domestic Conferences
  • Patents
• Photo
• Dataset
• Contact

Contact

• C129, The 3rd Engineering Building, Yonsei University, 50 Yonsei-ro, Seodaemun-Gu, Seoul 120-749, Korea
• Phone: +82-2-2123-2879
  Fax: +82-2-313-2879
  Email: khsohnyonsei.ac.kr

Home | Introduction | Research | People | Lecture | Publications | Photo | Dataset | Contact

© 2012 Digital Image Media Lab @ Yonsei University