Seung-Hwan Baek

(pronunciation)

[CV] [LinkedIn] [Google Scholar] shwbaek [at] postech [dot] ac [dot] kr

I'm a new assistant professor at POSTECH Computer Graphics Lab affiliated with the CSE department and the graduate school of AI. Before joining POSTECH, I worked as a post-doctoral research associate at Princeton University and hold a Ph.D. degree in Computer Science from KAIST.

[NEWS]

  • [2022 Mar.] Our obstruction-cloaking paper has been accepted at SIGGRAPH 2022.

  • [2022 Mar.] Our 3D time-of-flight imaging paper has been accepted at TOG.

  • [2022 Mar.] Our polarimetric 3D imaging paper has been accepted at CVPR 2022.

  • [2022 Mar.] Our glass segmentation paper has been accepted at CVPR 2022.

  • [2021 Dec.] Our learned metalens imaging paper has been accepted at Nature Communications.

  • [2021 Aug.] Our polarimetric imaging has been accepted at SIGGRAPH Asia 2021.

  • [2021 Aug.] Our learned hyperspectral 3D imaging paper has been accepted at ICCV 2021.

  • [2021 Mar.] Our learned 3D multi-view imaging paper has been accepted at CVPR 2021, oral.

  • [2021 Mar.] Our time-of-flight 3D reconstruction paper has been accepted at CVPR 2021.

Research Areas: Computer Graphics and Vision

Computational imaging
learning-based camera design, hyperspectral imaging, polarimetric imaging, ToF imaging

3D reconstruction
geometry and appearance acquisition

Computational photography
image restoration and synthesis

My research interests lie in computer graphics and computer vision with a particular focus on computational imaging and display. I aim to capture, model, and analyze the high-dimensional visual information of the real world originating from complex interplays between light, material appearance, and geometry. To this end, I design end-to-end computational imaging and display systems for fundamental scientific analysis as well as diverse application domains, including mobile cameras, autonomous vehicles, VR/AR displays, and scientific instruments.

Members

Youngchan Kim

Seokjun Choi

Our group explores the frontier of graphics, vision, and imaging.

  • Prospective graduate students

    • Send me an email with your CV, research interest, and transcripts.

  • Undergraduate students

    • Feel free to send me an email for a potential research opportunity!

Publications

2022

[TOP] Seeing Through Obstructions with Diffractive Cloaking
Zheng Shi, Yuval Bahat, Seung-Hwan Baek, Qiang fu, Hadi Amata, Xiao Li, Praneeth Chakravarthula, Wolfgang Heidrich, Felix Heide
ACM Transactions on Graphics (Proc. SIGGRAPH 2022)

[PDF] [Supple]

[TOP] Centimeter-Wave Free-Space Time-of-Flight Imaging
Seung-Hwan Baek*, Noah Walsh*, Ilya Chugunov, Zheng Shi, Felix Heide
ACM Transactions on Graphics (presented at SIGGRAPH 2022)

Pupil-aware Holography
Praneeth Chakravarthula, Seung-Hwan Baek, Ethan Tseng, Andrew Maimone, Grace Kuo, Florian Schiffers, Nathan Matsuda, Oliver Cossairt, Douglas Lanman, Felix Heide
Arxiv, 2022

[PDF]

[TOP] All-photon Polarimetric Time-of-Flight Imaging
Seung-Hwan Baek, Felix Heide
IEEE Computer Vision and Pattern Recognition (CVPR) 2022

[PDF] [Supple]

[TOP] Glass Segmentation using Intensity and Spectral Polarization Cues
Haiyang Mei , Bo Dong , Wen Dong , Jiaxi Yang , Seung-Hwan Baek, Felix Heide, Pieter Peers , Xiaopeng Wei , Xin Yang
IEEE Computer Vision and Pattern Recognition (CVPR) 2022

2021

Neural Etendue Expander for Ultra-Wide-Angle High-Fidelity Holographic Display
Seung-Hwan Baek*, Ethan Tseng*, Andrew Maimone, Nathan Matsuda, Grace Kuo, Qiang Fu, Wolfgang Heidrich, Douglas Lanman, Felix Heide
Arxiv, 2021

[PDF]

[TOP] Polarimetric Spatio-Temporal Light Transport Probing
Seung-Hwan Baek, Felix Heide
ACM Transactions on Graphics (Proc. SIGGRAPH Asia 2021)

[Project] [PDF] [Supple] [Code]

Neural Nano-Optics for High-quality Thin Lens Imaging
Ethan Tseng*, Shane Colburn*, James Whitehead, Luocheng Huang, Seung-Hwan Baek, Arka Majumdar, Felix Heide
Nature Communications, 2021

[TOP] Single-shot Hyperspectral-Depth Imaging with Learned Diffractive Optics
Seung-Hwan Baek, Hayato Ikoma, Daniel S. Jeon, Yuqi Li, Wolfgang Heidrich, Gordon Wetzstein, Min H. Kim
IEEE International Conference on Computer Vision (ICCV), 2021

[TOP] Polka Lines: Learning Structured Illumination and Reconstruction for Active Stereo
Seung-Hwan Baek, Felix Heide
IEEE Computer Vision and Pattern Recognition (CVPR) 2021, oral

[TOP] Mask-ToF: Learning Microlens Masks for Flying Pixel Removal in Time-of-Flight Imaging
Ilya Chugunov, Seung-Hwan Baek, Qiang Fu, Wolfgang Heidrich, Felix Heide
IEEE Computer Vision and Pattern Recognition (CVPR) 2021

Neural Ray-Tracing: Learning Surfaces and Reflectance for Relighting and View Synthesis
Julian Knodt, Joe Bartusek, Seung-Hwan Baek, Felix Heide
Arxiv, 2021

[PDF]

2020

Progressive Acquisition of SVBRDF and Shape in Motion
Hyunho Ha, Seung-Hwan Baek, Giljoo Nam, Min H. Kim
Computer Graphics Forum, 2020

[TOP] Image-Based Acquisition and Modeling of Polarimetric Reflectance
Seung-Hwan Baek, Tizian Zeltner, Hyun Jin Ku, Inseung Hwang, Xin Tong, Wenzel Jakob, Min H. Kim
ACM Transactions on Graphics (Proc. SIGGRAPH 2020)

[TOP] Single-shot Monocular RGB-D Imaging using Uneven Double Refraction
Andreas Meuleman*, Seung-Hwan Baek*, Felix Heide, Min H. Kim
IEEE Computer Vision and Pattern Recognition (CVPR) 2020, oral

2019

[TOP] Compact Snapshot Hyperspectral Imaging with Diffracted Rotation
Daniel S. Jeon, Seung-Hwan Baek, Shinyoung Yi, Qiang Fu, Xiong Dun, Wolfgang Heidrich, Min H. Kim
ACM Transactions on Graphics (Proc. SIGGRAPH 2019)

[Ph.D. Thesis] Computational Imaging with Light Waves
Seung-Hwan Baek
Ph.D. thesis, KAIST, Computer Science, 2019
Outstanding thesis award at KAIST
Doctoral consortium at SIGGRAPH Asia 2018

2018

[TOP] Simultaneous Acquisition of Polarimetric SVBRDF and Normals
Seung-Hwan Baek, Daniel S. Jeon, Xin Tong, Min H. Kim.
ACM Transactions on Graphics (Proc. SIGGRAPH Asia 2018)

[TOP] Enhancing the Spatial Resolution of Stereo Images using a Parallax Prior
Daniel S. Jeon, Seung-Hwan Baek, Inchang Choi, Min H. Kim.
IEEE Computer Vision and Pattern Recognition (CVPR) 2018

2017

[TOP] Compact Single-Shot Hyperspectral Imaging using a Prism
Seung-Hwan Baek, Incheol Kim, Diego Gutierrez, Min H. Kim.
ACM Transactions on Graphics (Proc. SIGGRAPH Asia 2017)

Reconstructing Interlaced High-Dynamic-Range Video using Joint Learning
Inchang Choi, Seung-Hwan Baek, Min H. Kim.
Transactions on Image Processing (TIP), 2017

Urban Image Stitching using Planar Perspective Guidance
Joo Ho Lee, Seung-Hwan Baek, Min H. Kim.
British Machine Vision Conference (BMVC 2017)

2016

[TOP] Birefractive Stereo Imaging for Single-Shot Depth Acquisition
Seung-Hwan Baek, Diego Gutierrez, Min H. Kim.
ACM Transactions on Graphics (Proc. SIGGRAPH Asia 2016)
KAIST's Top 10 Research Accomplishments

Electrothermal MEMS Parallel Plate Rotation for Single-imager Stereoscopic Endoscopes
Kyung-Won Jang, Sung-Pyo Yang, Seung-Hwan Baek, Min-Suk Lee, Hyeon-Cheol Park, Yeong-Hyeon Seo, Min H. Kim, Ki-Hun Jeong.
OSA Optics Express (OE), 2016

[PDF]

[TOP] Multiview Image Completion with Space Structure Propagation
Seung-Hwan Baek, Inchang Choi, Min H. Kim.
IEEE Computer Vision and Pattern Recognition (CVPR) 2016

Stereo Fusion: Combining Refractive and Binocular Disparity
Seung-Hwan Baek, Min H. Kim.
Computer Vision and Image Understanding (CVIU) 2016

2015

[Master Thesis] Stereo Fusion using a Refractive Medium on a Binocular Base
Seung-Hwan Baek
Master thesis, KAIST 2015

Outstanding M.S. thesis award

[PDF]

2014

Stereo Fusion using a Refractive Medium on a Binocular Base
Seung-Hwan Baek, Min H. Kim.
Asian Conference on Computer Vision (ACCV) 2014, oral
Best application paper award and best demo award