CV

A PDF version of my full CV is available here.

Education

Ph.D. in Electrical Engineering, KAIST

Thesis: 4D Scene Reconstruction based on Dynamic 3D Gaussian Splatting using Global-to-Local Motion Decomposition
Advisor: Prof. Munchurl Kim
GPA: 4.01 / 4.3

Mar. 2021 – Feb. 2026

M.S. in Electrical Engineering, KAIST

Thesis: An Extended Least Difference Greedy Clique-Cover Algorithm for Index Coding
Advisor: Prof. Youngchul Sung
GPA: 3.98 / 4.3

Mar. 2012 – Feb. 2014

B.S. in Electrical and Electronic Engineering, Yonsei University

National Science & Engineering Scholarship (Full tuition)
GPA: 3.57 / 4.3

Mar. 2008 – Feb. 2012

Research Experience

Senior Researcher, Media Research Division, ETRI

Mar. 2014 – Present

Research Interests

Immersive video and computer vision applications, including:
3D/4D scene representation, novel view synthesis, video coding for machines.

Publications

International Conferences

MoRel: Long-Range Flicker-Free 4D Motion Modeling Anchor Relay-based Bidirectional Blending via with Hierarchical Densification

S. Kwak*, W. Kwon*, J. Jeong, G. Kim, W.-S. Cheong, J. Oh, "MoRel: Long-Range Flicker-Free 4D Motion Modeling Anchor Relay-based Bidirectional Blending via with Hierarchical Densification," in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. ⭐ Highlight

Tracking-based adaptive temporal resampling for video coding for machines

E. An, M. Kim, K. Seo, S. Kwak, A. Kim, S. Jung, H. Choo, "Tracking-based adaptive temporal resampling for video coding for machines," in IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS), 2025.

MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting

S. Kwak, J. Kim, J. Jeong, W.-S. Cheong, J. Oh, M. Kim, "MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting," in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

Adaptive Image Downscaling for Rate-Accuracy-Latency Optimization of Task-Target Image Compression

H. Choi, S. Jeong, S. Kwak, S. Jung, J. Ko, "Adaptive Image Downscaling for Rate-Accuracy-Latency Optimization of Task-Target Image Compression," in IEEE 6th International Conference on AI Circuits and Systems (AICAS), 2024.

Machine-Attention-based Video Coding for Machines

Y. Lee, S. Kim, K. Yoon, H. Lim, S. Kwak, H. Choo, "Machine-Attention-based Video Coding for Machines," in IEEE International Conference on Image Processing (ICIP), 2023.

Partial Access using Group-based MPEG Immersive Video Coding Technology

G. Lee, S. Kwak, H. Shin, B. Lee, W.-S. Cheong, "Partial Access using Group-based MPEG Immersive Video Coding Technology," in International Conference on 3D Systems and Applications (3DSA), 2023.

A Study on the Effect of Total Variation Regularizer in Voxel Grid-based Radiance Field

S. Kwak, J. Jeong, J. Kim, G. Lee, W.-S. Cheong, M. Kim, "A Study on the Effect of Total Variation Regularizer in Voxel Grid-based Radiance Field," in International Conference on 3D Systems and Applications (3DSA), 2023.

Feature-Guided Machine-Centric Image Coding for Downstream Tasks

S. Kwak, J. Yun, H. Choo, M. Kim, "Feature-Guided Machine-Centric Image Coding for Downstream Tasks," in IEEE International Conference on Multimedia and Expo (IEEE ICMEW), 2023.

A Study on VCM Anchor Generation for Object Segmentation

G. Um, S. Kwak, J. Yun, W.-S. Cheong, J. Seo, "A Study on VCM Anchor Generation for Object Segmentation," in International Conference on Information and Communication Technology Convergence (ICTC), 2020.

An Improved View Synthesis of Light Field Images for Supporting 6 Degrees-of-Freedom

S. Kwak, J. Yun, W.-S. Cheong, J. Seo, "An Improved View Synthesis of Light Field Images for Supporting 6 Degrees-of-Freedom," in The 26th International Display Workshops (IDW), Nov. 2019. (Oral)

A Study on the Virtual View Synthesis for Omnidirectional Images

S. Kwak, J. Yun, W.-S. Cheong, J. Seo, "A Study on the Virtual View Synthesis for Omnidirectional Images," in 10th International Conference on 3D System and Applications (3DSA), Aug. 2018. (Oral)

Design and Performance Evaluation of Physical Layer Security Communication System based on Coded FTN with Soft Re-Modulation Technique

M.-S. Baek, S. Kwak, Y. Kim, N. Hur, "Design and Performance Evaluation of Physical Layer Security Communication System based on Coded FTN with Soft Re-Modulation Technique," in 2017 Future Generation Communication and Networking (FGCN), Nov. 2017.

On the Spectral Analysis of Discrete-Time Faster-Than-Nyquist Signaling

S. Kwak, J. Yun, H. Lim, N. Hur, "On the Spectral Analysis of Discrete-Time Faster-Than-Nyquist Signaling," in IEEE 19th International Conference on Advanced Communication Technology (ICACT), Feb. 2017. (Oral)

Physical layer security based on coded FTN signaling for premium services in satellite digital broadcasting system

M.-S. Baek, J. Yun, S. Kwak, H. Lim, Y. Kim, N. Hur, "Physical layer security based on coded FTN signaling for premium services in satellite digital broadcasting system," in 2017 IEEE International Conference on Consumer Electronics (ICCE), Jan. 2017.

Performance Evaluation of Faster-Than-Nyquist Signaling with BCJR Interference Cancellation Technique in TU-6 Channel Mode

M.-S. Baek, Y. Kim, J. Yun, S. Kwak, N. Hur, H. Lim, "Performance Evaluation of Faster-Than-Nyquist Signaling with BCJR Interference Cancellation Technique in TU-6 Channel Mode," in 2015 7th International Conference on Multimedia, Computer Graphics and Broadcasting (MulGraB), Nov. 2015.

Some new results on index coding when the number of data is less than the number of receivers

J. So, S. Kwak, Y. Sung, "Some new results on index coding when the number of data is less than the number of receivers," in 2014 IEEE International Symposium on Information Theory (ISIT), Jul. 2014.

An Extended Least Difference Greedy Clique-Cover Algorithm for Index Coding

S. Kwak, J. So, Y. Sung, "An Extended Least Difference Greedy Clique-Cover Algorithm for Index Coding," in 2014 IEEE International Symposium on Information Theory (ISIT), Jul. 2014.

Journal Articles

Adaptive spatial down-sampling method based on object occupancy distribution for video coding for machines

E. An, A. Kim, S. Jung, S. Kwak, J. Lee, W.-S. Cheong, K. Seo, "Adaptive spatial down-sampling method based on object occupancy distribution for video coding for machines," EURASIP Journal on Image and Video Processing, Vol. 36, No. 1, Oct. 2024.

Ray tracing-based construction of 3D background model for real-time stereoscopic rendering of live immersive video

Y. Kim, J. Yun, S. Kwak, I. Ihm, "Ray tracing-based construction of 3D background model for real-time stereoscopic rendering of live immersive video," Virtual Reality, 28(1), 17, Jan. 2024.

View Synthesis with Sparse Light Field for 6DoF Immersive Video

S. Kwak, J. Yun, J.-Y. Jeong, Y. Kim, I. Ihm, W.-S. Cheong, J. Seo, "View Synthesis with Sparse Light Field for 6DoF Immersive Video," ETRI Journal, Vol. 44, No. 1, Feb. 2022.

A Supplementary Explanation for Experimental Environment of “Implementation Methodologies of Deep Learning-Based Signal Detection for Conventional MIMO Transmitters”

M.-S. Baek, S. Kwak, J.-Y. Jung, H. M. Kim, D.-J. Choi, "A Supplementary Explanation for Experimental Environment of `Implementation Methodologies of Deep Learning-Based Signal Detection for Conventional MIMO Transmitters`," IEEE Transactions on Broadcasting, Vol. 67, No. 1, Oct. 2020.

Implementation Methodologies of Deep Learning-based Signal Detection for Conventional MIMO Transmitters

M.-S. Baek, S. Kwak, J.-Y. Jung, H. M. Kim, D.-J. Choi, "Implementation Methodologies of Deep Learning-based Signal Detection for Conventional MIMO Transmitters," IEEE Transactions on Broadcasting, Vol. 65, No. 3, Sep. 2019.

Awards & Honors

Outstanding Paper Award, Korean Institute of Broadcast and Media Engineers (KIBME) Summer Conference, 2022
Outstanding Paper Award, Korea Information and Communication Society (KICS) Winter Conference, 2019
Outstanding Paper Award, International Conference on 3D Systems and Applications (3DSA), 2019
National Science and Technology Scholarship (Four years full tuition), Ministry of Science and Technology, Korea, 2008 – 2012

Projects

Spatial Computing Technologies (Jan. 2022 – Present)
- Development of immersive video spatial computing technology for ultra-realistic metaverse services
- Composition, transmission, synthesis, and rendering for immersive media streaming based on MPEG Immersive Video (MIV)
- Funded by ICT R&D program of MSIT/IITP
Video Coding for Machines (Jan. 2020 – Present)
- Developing video coding technologies optimized for machine analysis
- International standardization activity on MPEG Video Coding for Machines (VCM)
- Funded by ICT R&D program of MSIT/IITP
Fundamental Technologies on Light Field (Jan. 2017 – Dec. 2021)
- Audio/Video coding and light field media fundamental technologies for ultra-realistic tera-media
- Virtual view synthesis and rendering for 6DoF immersive media services to HMD users
- Funded by ICT R&D program of MSIT/IITP
Faster-Than-Nyquist Signaling (Jan. 2014 – Dec. 2016)
- Development of advanced broadcasting systems based on FTN
- FTN signaling and iterative interference cancellation to improve spectral efficiency
- Funded by ICT R&D program of MSIT/IITP

Professional Activities

International Standardization (ISO/IEC JTC1/SC29 MPEG, 2019 – Present)

Selected MPEG contributions:

m73774, [VCM] Modification of NNBDR decoding process
m72245 / m72243, [VCM] Postfilter / Prefilter network for VCM
m71305 / m71304, [VCM] Neural network based post- / pre-filter for VCM
m69990, [VCM] Learned joint filter network for VCM
m54409, [MPEG-I Visual] Ray-based blending weight for 6DoF view synthesis
m48769, [MPEG-I Visual] Improved Triangle Colorization of RVS for ERP

Invited Talks and Exhibitions

YouTube video, “Immersive 3D video without glasses,” ETRI IT Technology Report, Aug. 2025.
Exhibition, “Real-time 3D video synthesis and rendering spatial computing technology,” ETRI Conference, Jun. 2025.
Invited Talk, “Novel view synthesis for various types of immersive displays,” Optical Society of Korea Winter Conference, Dec. 2024.
Invited Talk & Exhibition, “6 Degrees-of-Freedom Immersive Media Technologies,” ETRI Conference, May 2022.
Exhibition, “Real-time view synthesis and rendering for omni-directional LF videos,” ETRI Communication and Media Technical Exhibition, Jan. 2022.
Invited Talk, “View synthesis and rendering for Immersive videos,” MPEG New Media Forum Technical Workshop, Nov. 2021.
Invited Talk, “Novel view synthesis for omni-directional light field videos,” ETRI Media Techday, Oct. 2020.

Reviewer

IEEE Transactions on Multimedia
IEEE Transactions on Visualization and Computer Graphics
IEEE Transactions on Circuits and Systems for Video Technology
ACM Multimedia
ETRI Journal

Patents

Granted

KR 2838985, Method and apparatus for encoding feature map, Jul. 22, 2025.
US 12293567, Feature-map-encoding method and apparatus for encoding and decoding a feature map for a neural network, May 6, 2025.
US 12170785, Method and apparatus for adaptive image preprocessing and reconstruction, Dec. 17, 2024.
US 11706395, Apparatus and method for selecting camera providing input images to synthesize virtual view images, Jul. 18, 2023.
US 11528461, Method and apparatus for generating virtual viewpoint image, Dec. 12, 2022.

Applications

US 19/170459, Method and apparatus for encoding feature map, Apr. 4, 2025.
US 19/086288, Method and device for viewport-based atlas selection, Mar. 21, 2025.
KR 2025-0007579, Method and apparatus for tracking-based adaptive temporal resampling for VCM, Jan. 17, 2025.
KR 2025-0002494, Method and apparatus for representing 3D dynamic scenes based on motion decomposition, Jan. 7, 2025.
KR 2024-0151557, Method and device for image pre-processing filtering for VCM, Oct. 30, 2024.
KR 2024-0092940, Method and device of learning based pre-processing filtering for video coding for machine, Jul. 15, 2024.
KR 2024-0039196, Method and device for viewport-based atlas selection, Mar. 21, 2024.
KR 2023-0170135, Method and apparatus of rate-adaptive video filtering for machines, Nov. 29, 2023.
US 18/514150, Method and apparatus for non-uniform super-resolution of image, Nov. 20, 2023.
KR 2022-0003596, Method and apparatus for image feature vector encoding for machine, Jan. 10, 2022.
KR 2022-0000334, Method and apparatus for combining warping images based on depth distribution, Jan. 3, 2022.
KR 2021-0164317, Method for adaptive pre-processing and restoring image for supporting human and machine simultaneously, Nov. 25, 2021.

Technology Transfer

Omnidirectional Virtual View Synthesizing and Rendering System, transferred to Overay, May 2024 (Contract value: 30M KRW).
Omnidirectional Virtual View Synthesizing and Rendering System, transferred to HanulSoft, Nov. 2023 (Contract value: 30M KRW).

Sangwoon Kwak

CV