Dongbo Min

Researcher (CV: updated on Feb. 10, 2012)
Advance Digital Science Center (ADSC)
Connexis North Tower, Singapore 138632

Ph. D (Digital Image Media Lab., Yonsei University, Republic of Korea)
Republic of Korea citizen

E-mail: dbmin99 at gmail dot com,  dongbo at adsc dot com dot sg
 Biography

I'm working with the Advanced Digital Sciences Center (ADSC) in Singapore, which was jointly founded by Univ. of Illinois at Urbana-Champaign (UIUC) and the Agency for Science, Technology and Research (A*STAR), a Singapore government agency. Before joining ADSC, I worked with the Mitsubishi Electric Research Laboratories (MERL) from 2009 to 2010, where I mainly developed a prototype of 3D video system (3DTV). I received the B.S., M.S. and Ph.D. degrees in electrical and electronic engineering from Yonsei University, Seoul, Korea in 2003, 2005 and 2009, respectively.


 Research Interest


 ▪ 3D video processing and computer vision
   - Stereo matching with spatial & temporal coherences
   - Image-based rendering
   - 3D scene/object reconstruction
   - Visual tracking and recognition
 ▪ 3D video coding
   - Depth video coding and its application to multiview video coding
   - Depth estimation for multiview video coding
 ▪ Computational photography for 3D video
   - Super-resolution/high dynamic range imaging (HDR) for multiview video
 ▪ Video processing using sparse representation
   - 2D video denoising/super-resolution with a patch based sparse representation
 ▪ Hybrid sensor system
   - High definition depth video estimation by fusion of CCD, infrared and active depth sensor
　

 Education


Ph. D. in Electrical and Electronics Engineering                                Mar. 2005 ~ Feb. 2009
Yonsei University, Seoul, Korea
Graduation thesis:
 ▪ Multiview Stereo Matching and Freeview Video Generation for 3DTV System
 ▪ Supervisor: Prof. Kwanghoon Sohn

M. S. in Electrical and Electronics Engineering                                 Mar. 2003 ~ Feb. 2005
Yonsei University, Seoul, Korea
Graduation thesis:
 ▪ Edge-preserving Joint Motion/Disparity Estimation In Stereo Image Sequences
 ▪ Supervisor: Prof. Kwanghoon Sohn

B. S. in Electrical and Electronics Engineering                                  Mar. 1999 ~ Feb. 2003
Department of Electrical and Electronics Engineering
Yonsei University, Seoul, Korea
　

 Research Experience


Advance Digital Science Center (ADSC)                                                                  Singapore
Researcher                                                                                                      July. 2010 - present

• Research topics
  - Developing a real-time application with 3D video
  - Developing 3D video processing technique using active range sensor
　

Mitsubishi Electric Research Laboratories (MERL)                           Cambridge, MA, USA
Post-Doc.                                                                                                   Jun. 2009 - Jun. 2010

• Research topics
  - Developed a prototype of 3D video system (3DTV)
  - Developed efficient and accurate depth estimation and occlusion handling methods for 3D video processing
  - Developed 3D video processing method with temporal coherence
  - Developed video enhancement methods using a patch based sparse representation
　

Yonsei University                                                                                                  Seoul, Korea
Research Assistant                                                                                   Mar. 2003 - May. 2009

• Research and development of next generation intelligent broadcasting technology
  - Mar. 2003 - May 2009
  - Funded by Information Technology Research Center of Ministry of Knowledge Economy
  - Developed novel methods for stereo depth estimation, image-based rendering
  - Developed 3D virtual studio with multiple stereo cameras
  - Developed real-time 3D object modeling and interaction system in 3D virtual studio

•  SOC development for processing 3D media
  - Sep. 2003 - Aug. 2006
  - Funded by System IC 2010 project of Ministry of Knowledge Economy
  - Developed a real-time disparity estimation method
  - Manufactured a prototype of SOC for 3D video processing with a SOC company

•  Development of the core technology for 3DTV system
  - Sep. 2005- Aug. 2008
  - Funded by fostering project of Lab of Excellency of Korea Industrial Technology Foundation
  - Developed 3D video and audio capturing system for 3D multimedia production
  - Developed novel methods for multiview depth estimation, image-based rendering
  - Developed novel methods for 3D background modeling using hand-held stereo cameras
  - Developed hybrid sensor system with TOF (Time-Of-Flight) camera for 3D video generation
  - Develpoed novel methods for depth video coding

•  Camera tracking and 3D shape reconstruction
  - May. 2008 - Apr. 2009
  - Funded by Koreas Broadcasting System (KBS)
  - Developed a new stereo matching and registration algorithm for 3D model reconstruction in the structure-from-motion framework

 Publication

International Journal

  1. Yun Liang, Kyle Rupnow, Yinan Li, Dongbo Min, Minh N. Do, and Deming Chen, "High Level Synthesis: Productivity, Performance, and Software Constraints," Journal of Electrical and Computer Engineering. (accepted)

  2. Dongbo Min, Jiangbo Lu, and Minh N. Do, "Depth Video Enhancement Based on Weighted Mode Filtering," IEEE Trans. on Image Processing (TIP). (to appear)

    3. [The previous title of this paper was `Depth Video Enhancement Based on Joint Global Mode Filtering'.]

  3. Jinwook Choi, Dongbo Min, and Kwanghoon Sohn, "2D-Plus-Depth Bases Resolution and Frame-rate Up-conversion Technique for Depth Video," IEEE Trans. on Consumer Electronics, vol. 56, no. 4, pp. 2489-2497, Nov. 2010.

  4. Dongbo Min and Kwanghoon Sohn, "An asymmetric post-processing for correspondence problem," Signal Processing: Image Communication (SPIC), vol. 25, no. 2, pp. 130-142, Feb. 2010.

  5. Dongbo Min, Donghyun Kim, SangUn Yun, and Kwanghoon Sohn, "2D/3D freeview video generation for 3DTV system," Signal Processing: Image Communication (SPIC), vol. 24, no. 1-2, pp. 31-48, Jan. 2009. (Invited paper, special issue on 3DTV in SPIC)

  6. Dongbo Min and Kwanghoon Sohn, "Cost aggregation and occlusion handling with WLS in stereo matching," IEEE Trans. on Image Processing (TIP), vol. 17, no. 8, pp. 1431-1442, Aug. 2008.

  7. Donghyun Kim, Dongbo Min, and Kwanghoon Sohn, "A stereoscopic video generation method using stereoscopic display characterization and motion analysis," IEEE Trans. on Broadcasting (TB), vol. 54, no. 2, pp 188-197, June 2008.

  8. Hansung Kim, Donghyun Kim, Dongbo Min, and Kwanghoon Sohn, "A 3D modeling and free-view generation system using environmental stereo cameras," Int. Journal of Imaging Systems and Technology (IJIST), vol. 17, no. 6, pp. 367-378, April 2008.

  9. Dongbo Min, Hansung Kim, and Kwanghoon Sohn, "Edge-preserving joint motion disparity estimation in stereo image sequences," Signal Processing: Image Communication (SPIC), vol. 21, no. 3, pp. 252-271, Mar. 2006.

  10. Hansung Kim, Dongbo Min, Shinwoo Choi, and Kwanghoon Sohn, "Real-time disparity estimation using foreground segmentation for stereo sequences," Optical Engineering, vol. 45, no. 3, pp. 037402 1-10,Mar. 2006.

International Journal (submitted)

  1. Bumsub Ham, Dongbo Min, and Kwanghoon Sohn, "Robust Scale Space Filter with Second Order Partial Differential Equations," IEEE Trans. on Image Processing (TIP). (submitted)

  2. Viet-Anh Nguyen, Dongbo Min, and Minh N. Do, "Efficient Techniques for Depth Video Compression Using Weighted Mode Filtering," IEEE Trans. on Circuits and Systems for Video Technology (TCSVT). (submitted)

International Conference

  1. Dongbo Min, Jiangbo Lu, Viet-Anh Nguyen, and Minh N. Do, "Weighted mode filtering and its applications to depth video enhancement and coding," IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Mar. 2012. (Invited paper on special session)

  2. Jinwook Choi, Dongbo Min, Jiangbo Lu, and Kwanghoon Sohn, "Stereo Depth Video Enhancement Based on Temporal and Inter-view Coherences," IEEE Int. Conf. on Consumer Electronics (ICCE), Jan. 2012.

  3. Stefan Winkler and Dongbo Min, "Stereoscopic Image Quality Compendium," Proc. Int. Conf. on Information and Communication Systems (ICICS), Dec. 2011.

  4. Kyle Rupnow, Yun Liang, Yinan Li, Dongbo Min, Minh N. Do, and Deming Chen, "High Level Synthesis of Stereo Matching: Productivity, Performance, and Software Constraints," Int. Conf. on Field Programmable Technology (FPT), Nov. 2011. [FPT is one of top FPGA-related conferences.]

  5. Dongbo Min, Jiangbo Lu, and Minh N. Do, "A Revisit to Cost Aggregation in Stereo Matching: How Far Can We Reduce Its Computational Redundancy?," IEEE Int. Conf. on Computer Vision (ICCV), Nov. 2011. (oral presentation)

  6. Kyle Rupnow, Yun Liang, Dongbo Min, Minh N. Do, and Deming Chen, "Mobile 3D Vision - Algorithm & Platform Challenges," Field Programmable Logic and Applications (FPL) Workshop, 2011.

  7. Bumsub Ham, Dongbo Min, and Kwanghoon Sohn, "Cost Aggregation with Anisotropic Diffusion in Feature Space for Hybrid Stereo Matching," IEEE Int. Conf. on Image Processing (ICIP), Sep. 2011.

  8. Jiangbo Lu, Dongbo Min, Raman S. Pahwa, and Minh N. Do, "A Revisit to MRF-based Depth Map Super-resolution and Enhancement," IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), May 2011.

  9. Jinwook Choi, Dongbo Min, Donghyun Kim, and Kwanghoon Sohn, "3D JBU based depth video filtering for temporal fluctuation reduction," IEEE Int. Conf. on Image Processing (ICIP), Sep. 2010.

  10. Dongbo Min, Sehoon Yea, and Anthony Vetro, "Occlusion handling based on support and decision," IEEE Int. Conf. on Image Processing (ICIP), Sep. 2010.

  11. Dongbo Min, Sehoon Yea, and Anthony Vetro, "Temporally consistent stereo matching using coherence function," IEEE 3DTV Conference, Jun. 2010.

  12. Dongbo Min, Sehoon Yea, Zafer Arican, and Anthony Vetro, "Disparity search range estimation: enforcing temporal consistency," IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Mar. 2010.

  13. Jinwook Choi, Dongbo Min, Bumsub Ham, and Kwanghoon Sohn, "Spatial and temporal up-conversion technique for depth video ," IEEE Int. Conf. on Image Processing (ICIP), Nov. 2009.

  14. Bumsub Ham, Dongbo Min, Jinwook Choi, and Kwanghoon Sohn, "Virtual view rendering using super-resolution with multiview images," IEEE Int. Conf. on Image Processing (ICIP), Nov. 2009.

  15. Bumsub Ham, Dongbo Min, and Kwanghoon Sohn, "Virtual view rendering using multiple stereo images," Proc. IWAIT, Jan. 2009.

  16. Donghyun Kim, Dongbo Min, Juhyun Oh, S. Jeon, and Kwanghoon Sohn, "Depth map quality for three-dimensional video," Proc. SPIE Electronic Imaging, Jan. 2009.

  17. Dongbo Min, Juhyun Oh, and Kwanghoon Sohn, "Asymmetric post-processing for stereo correspondence," IEEE Int. Conf. on Pattern Recognition (ICPR), Dec. 2008.

  18. Dongbo Min, Donghyun Kim, and Kwanghoon Sohn, "2D/3D freeview video generation for 3DTV system," IEEE Int. Conf. on Image Processing (ICIP), pp. 1760-1763, Oct. 2008.

  19. Dongbo Min, Donghyun Kim, and Kwanghoon Sohn, "Virtual view rendering system for 3DTV," IEEE 3DTV Conference, pp. 249-252, May 2008.

  20. Dongbo Min, Donghyun Kim, SangUn Yun, and Kwanghoon Sohn, "Freeview rendering with trinocular camera," IEEE Int. Symposium on Circuits and Systems (ISCAS), pp. 3446-3449, May 2008.

  21. Dongbo Min and Kwanghoon Sohn, "Stereo matching with asymmetric occlusion handling in weighted least square framework," IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pp. 1061-1064, March 2008.

  22. SangUn Yun, Dongbo Min, and Kwanghoon Sohn, "3D Scene Reconstruction System with Hand-held Stereo Cameras," IEEE 3DTV Conference, May. 2007.

  23. Donghyun Kim, Dongbo Min, and Kwanghoon Sohn, "Stereoscopic video generation method using motion analysis," IEEE 3DTV Conference, May. 2007.

  24. SangUn Yun, Dongbo Min, and Kwanghoon Sohn, "Fast dense stereo matching using adaptive window in hierarchical framework," Int. Symposium on Visual Computing (ISVC), LNCS, pp. 316-325, Nov. 2006.

  25. Dongbo Min, SangUn Yun, and Kwanghoon Sohn, "Segment-based Stereo Matching Using Energy-based Regularization," Proc. IWMRCS, LNCS, pp. 761-768, Sep. 2006.

  26. Dongbo Min and Kwanghoon Sohn, "Edge-preserving Simultaneous Joint Motion-Disparity Estimation," Int. Conf. on Pattern Recognition (ICPR), pp. 252-271, August. 2006.

  27. Hansung Kim, Dongbo Min, Shinwoo Choi, Donghyun Kim, and Kwanghoon Sohn, "Real-time shape recovery from silhouette and disparity," SIGGRAPH (sketch paper), July 2005.

  28. Hansung Kim, Dongbo Min, and Kwanghoon Sohn, "Real-Time Stereo Using Foreground Segmentation and Hierarchical Disparity Estimation," Pacific-Rim Conference on Multimedia (PCM), LNCS, pp. 384-395, Nov. 2005.

  29. Dongbo Min, Hansung Kim, Shinwoo Choi, and Kwanghoon Sohn, "Edge-Preserving Joint Motion Disparity Estimation in Stereo Image Sequences," Proc. of IASTED Signal and Image Processing, pp. 471-176, Aug. 2004.

    30.

International Conference (submitted)

  1. Bumsub Ham, Dongbo Min, and Kwanghoon Sohn, "A revisit to anisotropic diffusion: a new diffusion smoothing with specific heat capacity in thermal diffusivity," IEEE Int. Conf. on Image Processing (ICIP), 2012. (submitted)

  2. Viet-Anh Nguyen, Dongbo Min, and Minh N. Do, "Efficient Edge-Preserving Interpolation and In-Loop Filters for Depth Map Compression," IEEE Int. Conf. on Image Processing (ICIP), 2012. (submitted)

    3.

Korean Journal/Conference
    2 papers/8 papers (in Korean)
 Demo Videos

1. 2D/3D Freeview video clips (zip)
- These video clips are examples about 2D/3D freeview video generation. For more detailed information, please refer to the following papers.
- 2D/3D freeview video generation for 3DTV system, SPIC 2009 (Its preliminary version was published in ICIP 2008).


2. Depth video enhancement
- These video clips are examples that show how to enhance quality of depth video, given noisy and low-resolution input depth video and corresponding high-quality color video.
- In general, the quality of depth video can be measured by the amount of noise, spatial resolution and temporal consistency.
- Experiments were performed for both 1) without and 2) with temporal consistency.

- Example 1 using computer-generated depth video (Tank) of Microsoft Research (MSR) Cambridge (after adding Gaussian noise)
  : Comparison of two results 1) without and 2) with temporal consistency: wmv file

- Example 2 using depth (Mesa Imaging SR4000) and color (Point Grey Flea) cameras
  : Input depth video clip (NN interpolation): wmv file
  : Results - 1) without temporal consistency: wmv file, 2) with temporal consistency: wmv file

Last updated: Feb. 10, 2012