Sunghoon Im Associate Professor Computer Vision Lab. Dept. Electrical Engineering and Computer Science (EECS), DGIST Dept. Interdisciplinary Studies of Artificial Intelligence (AI), DGIST Email: sunghoonim [at] dgist.ac.kr CV | Google Scholar | dblp | Github | Linkedin

I am an associate professor at the Department of Electrical Engineering and Computer Science (EECS) and the Department of Interdisciplinary Studies of Atrificial Intelligence (AI) at DGIST, South Korea, working as a faculty member of DGIST Computer Vision Lab. My research lies in the areas of computer vision and machine learning, especially in the problem of 3D reconstruction, Scene understanding, Image/Video synthesis and Vision for new-type sensors.

I received my M.S and Ph.D degrees in Electrical Engineering from KAIST, Korea in 2016 and 2019 respectively. During my graduate study, I worked at the Robotics and Computer Vision Lab with Prof. In So Kweon as my advisor. I was research intern at Microsoft Research, Beijing in 2018, and visiting scholar at Carnegie Mellon University in 2019. I received my Bachelor degree in Electronic Engineering from Sogang university (Summa cum laude) in 2014.

• International Journals

	A Study on the Generality of Neural Network Structures for Monocular Depth Estimation Jinwoo Bae, Kyumin Hwang, Sunghoon Im IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 [Paper]
	RVMOS: Range-View Moving Object Segmentation leveraged by Semantic and Motion Features Jaeyeul Kim*, Jungwan Woo*, Sunghoon Im IEEE Robotics and Automation Letters (RAL), 2022 Presented at IEEE/RSJ International Conference on Intelligence Robots and Systems (IROS), 2022 [Paper]
	Self-supervised Monocular Depth and Motion Learning in Dynamic Scenes: Semantic Prior to Rescue Seokju Lee, Francois Rameau, Sunghoon Im, In So Kweon International Journal of Computer Vision (IJCV), 2022 [Paper]
	CMSNet: Deep Color and Monochrome Stereo Hae-Gon Jeon, Sunghoon Im, Jaesung Choe, Minjun Kang, Joon-Young Lee, Martial Hebert International Journal of Computer Vision (IJCV), Jan 2022 [Paper]
	A Large-scale Virtual Dataset and Egocentric Localization for Disaster Responses Hae-Gon Jeon, Sunghoon Im, Byeong-Uk Lee, François Rameau, Dong-Geol Choi, Jean Oh, In So Kweon, Martial Hebert IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 [Paper]
	Deep Depth from Uncalibrated Small Motion Clip Sunghoon Im, Hyowon Ha, Hae-Gon Jeon, Stephen Lin, In So Kweon IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Apr 2021 - Selected as Outstanding Research Achievement of GIST [Paper]
	Ring Difference Filter for Fast and Noise Robust Depth from Focus Hae-Gon Jeon, Jaeheung Surh, Sunghoon Im, In So Kweon IEEE Transactions Image Processing (TIP), Dec 2020 [Paper]
	Robust Depth Estimation using Auto-Exposure Bracketing Sunghoon Im, Hae-Gon Jeon, In So Kweon IEEE Transactions Image Processing (TIP), May 2019 [Paper]
	Accurate 3D Reconstruction from Small Motion Clip for Rolling Shutter Cameras Sunghoon Im, Hyowon Ha, Gyeongmin Choe, Hae-Gon Jeon, Kyungdon Joo, In So Kweon IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Apr 2019 [Paper]
	RANUS: RGB and NIR Urban Scene Dataset for Deep Scene Parsing Gyeongmin Choe, Seong-heum Kim, Sunghoon Im, Joon-Young Lee, Srinivasa Narasimhan, In So Kweon IEEE Robotics and Automation Letters (RAL), July 2018 [Paper]
	Geometry Guided 3D Propagation for Depth from Small Motion Seunghak Shin, Sunghoon Im, Inwook Shim, Hae-Gon Jeon, In So Kweon IEEE Signal Processing Letters (SPL), Dec 2017 [Paper]

• International Conferences

	Offline-to-Online Knowledge Distillation for Video Instance Segmentation Hojin Kim, Seunghun Lee, Hyun Kang, Sunghoon Im IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024 [Paper]
	Implicit Neural Image Stitching With Enhanced and Blended Feature Reconstruction Minsu Kim, Jaewon Lee, Byeonghun Lee, Sunghoon Im, Kyeonghwan Jin IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024 [Paper]
	Depth-discriminative Metric Learning for Monocular 3D Object Detection Wonhyeok Choi, Mingyu Shin, Sunghoon Im Neural Information Processing Systems (NeurIPS), 2023 [Paper]
	Multi-Target Domain Adaptation with Class-Wise Attribute Transfer in Semantic Segmentation Changjae Kim, Seunghun Lee, Sunghoon Im British Machine Vision Conference (BMVC), 2023 [Paper]
	Rotation Matters: Generalized Monocular 3D Object Detection for Various Camera System Sungho Moon, Jinwoo Bae, Sunghoon Im IEEE Conference on Computer Vision and Pattern Recognition workshop (CVPRw), 2023 [Paper]
	Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies Wonhyeok Choi, Sunghoon Im IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [Paper]
	Deep Digging into the Generalization of Self-supervised Monocular Depth Estimation Jinwoo Bae, Sungho Moon, Sunghoon Im The Thirty-seventh AAAI Conference on Artificial Intelligence (AAAI), 2023 [Paper]
	Facial Depth and Normal Estimation using Single Dual-Pixel Camera Minjun Kang, Jaesung Choe, Hyowon Ha, Hae-Gon Jeon, Sunghoon Im, In So Kweon, Kuk-Jin Yoon European Conference on Computer Vision (ECCV), 2022 [Paper]
	ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation Seunghun Lee, Wonhyeok Choi, Changjae Kim, Minwoo Choi, Sunghoon Im IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 [Paper]
	ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack Dahoon Park, Kon-Woo Kwon, Sunghoon Im, Jaeha Kung British Machine Vision Conference (BMVC), 2021 [Paper]
	VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction Jaesung Choe, Sunghoon Im, François Rameau, Minjun Kang, In So Kweon IEEE International Conference on Computer Vision (ICCV), 2021 [Paper]
	ProFeat: Unsupervised Image Clustering via Progressive Feature Refinement Jeonghoon Kim, Sunghoon Im, Sunghyun Cho CVPR workshop on Learning From Limited or Imperfect Data (CVPRw), 2021 [Paper]
	DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation Seunghun Lee, Sunghyun Cho, Sunghoon Im IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 [Paper]
	Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021 - Qualcomm Innovation Fellowship Korea 2020 - Silver Prize, 16th Samsung Electro-Mechanics Best Paper Awards [Paper][Project page][Source code]
	Instance-wise Depth and Motion Learning from Monocular Videos Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon NeurIPS workshop on Machine Learning for Autonomous Driving (NeurIPSw), 2020 NeurIPS workshop on Differentiable computer vision, graphics, and physics in machine learning (NeurIPSw), 2020 Honorable Mention, 12th Electronic Times ICT Paper Contest [Paper] [Project page]
	Learning Shape-based Representation for Visual Localization in Extremely Changing Conditions Hae-Gon Jeon, Sunghoon Im, Jean Oh, Martial Hebert IEEE International Conference on Robotics and Automation (ICRA), 2020 [Paper] [Project page]
	DISC: A Large-scale Virtual Dataset for Simulating Disaster Scenarios Hae-Gon Jeon, Sunghoon Im, Byeong-Uk Lee, Dong-Geol Choi, Martial Hebert, In So Kweon / IEEE/RSJ International Conference on Intelligence Robots and Systems (IROS), 2019 [Paper] [Project page]
	Learning Residual Flow as Dynamic Motion from Stereo Video Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon IEEE/RSJ International Conference on Intelligence Robots and Systems (IROS), 2019 [Paper] [Project page]
	DPSNet: End-to-end Deep Plane Sweep Stereo Sunghoon Im, Hae-Gon Jeon, Stephen Lin, In So Kweon International Conference on Learning Representations (ICLR), 2019 [Paper] [Source code]
	Depth Completion with Deep Geometry and Context Guidance Byeong-Uk Lee, Hae-Gon Jeon, Sunghoon Im, In So Kweon IEEE International Conference on Robotics and Automation (ICRA), 2019 [Paper]
	Robust Depth Estimation from Auto Bracketed Images Sunghoon Im, Hae-Gon Jeon, In So Kweon IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 - Best Poster Award, Samsung AI Forum 2018 [Paper]
	Noise Robust Depth from Focus using a Ring Difference Filter Jaeheung Surh, Hae-Gon Jeon, Yunwon Park, Sunghoon Im, Hyowon Ha, In So Kweon IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (Spotlight) [Paper] [Project page]
	All-around Depth from Small Motion with A Spherical Panoramic Camera Sunghoon Im, Hyowon Ha, Francois Rameau, Hae-Gon Jeon, Gyeongmin Choe, In So Kweon European Conference on Computer Vision (ECCV), 2016 - Best Poster Presentation Award, 29th IPIU 2017 [Paper] [Source code]
	High-quality Depth from Uncalibrated Small Motion Clip Hyowon Ha, Sunghoon Im, Jaesik Park, Hae-Gon Jeon, In So Kweon IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Oral) - Qualcomm Innovation Award, Qualcomm-KAIST Innovation Awards 2016 [Paper] [Source code]
	Stereo Matching with Color and Monochrome Cameras in Low-light Conditions Hae-Gon Jeon, Joon-Young Lee, Sunghoon Im, Hyowon Ha, In So Kweon IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 - Silver Prize, 22nd HumanTech Paper Award, Samsung Electronics Co., Ltd. - Best Poster Presentation Award, 29th IPIU 2017 [Paper]
	High Quality Structure from Small Motion for Rolling Shutter Cameras Sunghoon Im, Hyowon Ha, Gyeongmin Choe, Hae-Gon Jeon, Kyungdon Joo, In So Kweon IEEE International Conference on Computer Vision (ICCV), 2015 - Best Poster Award, IWRCV 2015 [Paper] [Source code]
	Depth from Accidental Motion using Geometry Prior Sunghoon Im, Gyeongmin Choe, Hae-Gon Jeon, In So Kweon IEEE International Conference on Image Processing (ICIP), 2015 (Top 10%) [Paper]

• Other Publications

• Depth Estimation from Light Field Cameras
  Sunghoon Im, Hae-Gon Jeon, Hyowon Ha, In So Kweon
  In Proc. of the 12th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Oct 2015.
• Relative Attributes with Deep Convolutional Neural Network
  Dong-jin Kim, Donggeun Yoo, Sunghoon Im, Namil Kim, T.Sirinukul wattana, In So Kweon
  In Proc. of the 12th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Oct 2015.

• Patents

• METHOD AND APPARATUS FOR ESTIMATING DEPTH USING RING DIFFERENCE FILTER
  Publication date: Sep 28, 2018. (10-2017-0091717)
• DEPTH MAP ACQUISITION DEVICE AND DEPTH MAP ACQUISITION METHOD
  Publication date: Apr 19, 2018. (10-2016-0103546)
• METHOD AND APPARATUS FOR ACQUIRING DEPTH MAP FROM ALL-AROUND CAMERA
  Publication date: Apr 17, 2018. (10-2016-0167525)
• DEPTH INFORMATION ACQUIRING DEVICE AND METHOD THEREOF
  Publication date: Aug 11, 2017. (10-2016-0076766)
• APPARATUS AND METHOD FOR DEPTH MAP GENERATION
  Publication date: Jun. 02, 2016. (10-2016-0015703)

• Academic Activities

• Teaching
  • Advanced Deep Learning, 2022.
  • Artificial Intelligence Basics, 2021.
  • Introduction to Deep Learning, 2020, 2021.
  • Deep Learning, 2020.
  • Computer Vision, 2019.
• Academic Services
  • Editor - IEIE Transactions on Smart Processing and Computing (SPC).
  • Web chair - Korean Conference on Computer Vision (KCCV) 2022.
  • Editor - The Information and Communications Technology Express (ICT Express).
  • Local chair - International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC)
• Reviewer (International Journal)
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
  • International Journal of Computer Vision (IJCV).
  • Computer Vision and Image Understanding (CVIU).
  • IEEE/ASME Transactions on Mechatronics (TMECH).
  • IEEE Transactions on Instrumentation and Measurement (TIM).
  • Pattern Recognition (PR).
  • Neurocomputing.
  • IEEE Robotics and Automation Letters (RAL)
  • IEEE Access.
  • International Journal of Control, Automation and Systems (IJCAS).
  • IEIE Transactions on Smart Processing and Computing (IEIE SPC).
  • Journal of Institute of Control, Robotics and System (ICROS).
• Reviewer (International Conference)
  • SIGGRAPH Asia 2022.
  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019-2023.
  • IEEE International Conference on Computer Vision (ICCV) 2019-2023.
  • European Conference on Computer Vision (ECCV) 2020-2022.
  • Conference on Neural Information Processing Systems (NeurIPS) 2020-2022.
  • International Conference on Machine Learning (ICML) 2020-2023.
  • International Conference on Learning Representations (ICLR) 2021-2023.
  • Association for the Advancement of Artificial Intelligence (AAAI) 2020-2023.
  • IEEE International Conference on Robotics and Automation (ICRA), 2021-2022.
  • IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2017.
  • Asian Conference on Computer Vision (ACCV) 2020.
  • IEEE Winter Conference on Applications of Computer Vision (WACV), 2020.
  • International Conference on 3D Vision (3DV) 2020.
  • International Conference on Control, Automation and Systems (ICCAS), 2020.
• Tutorial
  • Multiple View Geometry, KETI Sangam, Aug-Oct 2020.
• Talks
  • KICS Big data and Automobility Workshop, Online, Jun 2022.
  • ETRI (Electronics and Telecommunications Research Institute), Daegu, Apr 2022.
  • Dongguk University, Seoul, Oct 2021.
  • 31st Signal Processing Joint Conference, IEIE, Online, Sep 2021.
  • 2nd Korea Artificial Intelligence Conference, Jeju, Sep 2021.
  • Kyungpook National University, Daegu, Sep 2021.
  • KCCV (Korean Conference on Computer Vision), Seoul, Sep 2021.
  • The Korean Institute of Broadcast and Media Engineers, Gyeongju, Apr 2021.
  • ETRI (Electronics and Telecommunications Research Institute) Daejeon, Oct 2020.
  • ETRI (Electronics and Telecommunications Research Institute) Daegu, Oct 2020.
  • GIST, Jun 2020.
  • KETI (Korea Electronics Technology Institute) Sangam, Jan 2020.
  • POSTECH, Dec 2019.
  • KETI (Korea Electronics Technology Institute) Pangyo, Nov 2019.
  • DGIF (Daegu Technopolis Grand Innovation Festival), Oct 2019.
  • ETRI (Electronics and Telecommunications Research Institute) Daejeon, Sep 2019.
  • Sogang University, Sep 2019.
  • Lunit, Aug 2019.
  • SAIT (Samsung Advanced Institute of Technology), Apr 2019.
  • Koh Young Technology, Jan 2019.

• Awards & Honors

• Awards
  • Best Academic Award, DGIST, Sep 2021.
  • Excellent Student Award, 2018 Rearch Performance Evaluation, KAIST EE, Apr 2019.
  • Best Poster Award, 2018 Samsung AI Forum, Samsung Research, Sep 2018.
  • Excellent Intern Award, Microsoft Research Asia (MSRA), Aug 2018.
  • Honor Student Award, 2017 Reserch Performance Evaluation, KAIST EE, Apr 2018.
  • Kim Choong-Ki Award, 2016 Reserch Performance Evaluation, KAIST EE, Apr 2017.
  • Best Poster presentation Award, 29th Workshop on Image Processing and Image Understanding (IPIU), Feb 2017.
  • Qualcomm Innovation Award 2016, Qualcomm Korea Corp. and KAIST, Apr 2016.
  • Silver prize, 22nd HumanTech Paper Award, Samsung Electronics Co., Ltd., Feb 2016.
  • Official Best 10% Paper Selection, ICIP 2015 Organizing Committe, Sep 2015.
  • Summa Cum Laude, Sogang University, Feb 2014.
  • Silver Prize, Design project competition, Sogang University, Nov 2013.
  • Prize for the top first percential GPA, Sogang University, Sep 2011, Mar 2012, and Sep 2012.
• Honors
  • NeurIPS 2020 Top 10% of high-scoring reviewer, Oct 2020.
  • CVPR 2019 Doctoral Consortium, Jun 2019.
  • ICLR 2019 Travel Award, May 2019.
  • Microsoft Research Asia (MSRA) Fellowship 2018 Winner, Oct 2018.
  • International Computer Vision Summer School (ICVSS 2016), Jul 2016.
  • Global Ph.D Fellowship, National Research Foundation of Korea (about $20,000 + Full scholarship per year for 2+1 years).