I'm a Research Scientist at Adobe Research based in San Jose, CA. I obtained my BS, MS & PhD from KAIST, advised by Prof. Munchurl Kim. During my PhD, I worked mostly on low-level vision, in restoring and enhancing images and videos.
I had a great time as a Research Intern, and after that a Student Researcher, in Perception, Google Research in 2020 (Host: Orly Liba). In 2021, I was fortunate to work as a Research Intern at Adobe Research (Mentor: Jianming Zhang). I'm grateful to be a recipient of the Google PhD Fellowship.
[CV] [Google Scholar] [LinkedIn] [GitHub]
09.2022 – present Research Scientist, Adobe Research, San Jose, CA
In Controllable Image Synthesis Group, Creative Media Lab
07.2021 – 12.2021 Research Intern, Adobe Research, San Jose, CA (remote)
In Vision Group, Media Intelligence Lab
Worked on mask-guided depth map refinement
09.2020 – 01.2021 Student Researcher, Google Research, Mountain View, CA (remote)
Continued internship project (part-time)
06.2020 – 09.2020 Research Intern, Google Research, Mountain View, CA (remote)
In Gcam (computational photography team), Perception
Worked on high-quality image inpainting
09.2018 – 08.2022 Ph.D. in Electrical Engineering, KAIST
Advisor: Prof. Munchurl Kim
09.2016 – 08.2018 M.S. in Electrical Engineering, KAIST
Advisor: Prof. Munchurl Kim
02.2012 – 08.2016 B.S. in Electrical Engineering, KAIST
07.2014 – 08.2015 Exchange student at Institut National des Sciences Appliquées (INSA) Lyon, France
Yuanhao Cai, He Zhang, Kai Zhang, Yixun Liang, Mengwei Ren, Fujun Luan, Qing Liu, Soo Ye Kim, Jianming Zhang, Zhifei Zhang, Yuqian Zhou, Yulun Zhang, Xiaokang Yang, Zhe Lin, Alan Yuille, Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction, IEEE International Conference on Computer Vision (ICCV), 2025 [arXiv] [project page]
Shaoteng Liu, Tianyu Wang, Jui-Hsien Wang, Qing Liu, Zhifei Zhang, Joon-Young Lee, Yijun Li, Bei Yu, Zhe Lin, Soo Ye Kim†, Jiaya Jia†, Generative Video Propagation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025 (†co-corresponding authors) [arXiv] [project page]
Gemma Canet Tarrés, Zhe Lin, Zhifei Zhang, He Zhang, Andrew Gilbert†, John Collomosse†, Soo Ye Kim†, Multitwine: Multi-Object Compositing with Text and Layout Control, IEEE Conference on Computer Vision and Pattern Recognition (CVPR Highlight), 2025 (†co-corresponding authors) [arXiv] [project page]
Tianyu Wang, Jianming Zhang, Haitian Zheng, Zhihong Ding, Scott Cohen, Zhe Lin, Wei Xiong, Chi-Wing Fu, Luis Figueroa†, Soo Ye Kim†, MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025 (†co-corresponding authors) [arXiv]
Xin Yu, Tianyu Wang, Soo Ye Kim, Paul Guerrero, Xi Chen, Qing Liu, Zhe Lin, Xiaojuan Qi, ObjectMover: Generative Object Movement with Video Prior, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Xi Chen, Zhifei Zhang, He Zhang, Yuqian Zhou, Soo Ye Kim, Qing Liu, Yijun Li, Jianming Zhang, Nanxuan Zhao, Yilin Wang, Hui Ding, Zhe Lin, Hengshuang Zhao, UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics, IEEE Conference on Computer Vision and Pattern Recognition (CVPR Highlight), 2025 [arXiv] [project page]
Jinrui Yang, Qing Liu, Yijun Li, Soo Ye Kim, Daniil Pakhomov, Mengwei Ren, Jianming Zhang, Zhe Lin, Cihang Xie, Yuyin Zhou, Generative Image Layer Decomposition with Visual Effects, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025 [arXiv] [project page]
Hang Hua, Qing Liu, Lingzhi Zhang, Jing Shi, Soo Ye Kim, Zhifei Zhang, Yilin Wang, Jianming Zhang, Zhe Lin, Jiebo Luo, FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025 [arXiv] [project page]
Yizhi Song, Liu He, Zhifei Zhang, Soo Ye Kim, He Zhang, Wei Xiong, Zhe Lin, Brian Price, Scott Cohen, Jianming Zhang, Daniel Aliaga, Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment, International Conference on Learning Representations (ICLR), 2025 [arXiv] [project page]
Gemma Canet Tarrés, Zhe Lin, Zhifei Zhang, Jianming Zhang, Yizhi Song, Dan Ruta, Andrew Gilbert, John Collomosse, Soo Ye Kim, Thinking Outside the BBox: Unconstrained Generative Object Compositing, European Conference on Computer Vision (ECCV), 2024 [arXiv] [paper] [project page]
Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, He Zhang, Wei Xiong, Daniel Aliaga, IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024 [arXiv] [paper] [project page]
Junghun Cha*, Ali Haider*, Seoyun Yang, Hoeyeong Jin, Subin Yang, A F M Shahab Uddin, Jaehyoung Kim, Soo Ye Kim†, Sung-Ho Bae†, Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model, AAAI Conference on Artificial Intelligence (AAAI), 2024 (*equal contribution, †co-corresponding authors) [arXiv] [paper]
Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, Daniel Aliaga, ObjectStitch: Object Compositing with Diffusion Model, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [arXiv] [paper]
Agus Gunawan, Soo Ye Kim, Hyeonjun Sim, Jae-Ho Lee, Munchurl Kim, Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [arXiv] [paper] [project page]
Soo Ye Kim, Jianming Zhang, Simon Niklaus, Yifei Fan, Simon Chen, Zhe Lin, Munchurl Kim, Layered Depth Refinement with Mask Guidance, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 [arXiv] [paper] [project page] [GitHub] [poster] [video] [summary]
Soo Ye Kim, Kfir Aberman, Nori Kanazawa, Rahul Garg, Neal Wadhwa, Huiwen Chang, Nikhil Karnad, Munchurl Kim, Orly Liba, Zoom-to-Inpaint: Image Inpainting with High Frequency Details, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022 [arXiv] [paper] [GitHub] [poster]
Soo Ye Kim*, Hyeonjun Sim*, Munchurl Kim, KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 (*equal contribution) [arXiv] [paper] [GitHub] [poster] [video]
Soo Ye Kim*, Jihyong Oh*, Munchurl Kim, FISR: Deep Joint Frame Interpolation and Super-Resolution with a Multi-Scale Temporal Loss, AAAI Conference on Artificial Intelligence (AAAI), 2020 (*equal contribution) [arXiv] [paper] [GitHub] [poster] [Spotlight-PPT]
Soo Ye Kim*, Jihyong Oh*, Munchurl Kim, JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video, AAAI Conference on Artificial Intelligence (AAAI), 2020 (*equal contribution) [arXiv] [paper] [GitHub] [poster] [Spotlight-PPT]
Soo Ye Kim, Jihyong Oh, Munchurl Kim, Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applications, IEEE International Conference on Computer Vision (ICCV Oral), 2019 [arXiv] [paper] [GitHub] [poster] [Oral-PPT]
Soo Ye Kim, Jeongyeon Lim, Taeyoung Na, Munchurl Kim, Video Super-Resolution based on 3D-CNNs with Consideration of Scene Change, IEEE International Conference on Image Processing (ICIP), 2019 [paper] [GitHub] [electronic poster]
Extended paper: 3DSRnet : Video Super-Resolution using 3D Convolutional Neural Networks, arXiv: 1812.09079
Soo Ye Kim, Dae Eun Kim, Munchurl Kim, ITM-CNN : Learning the Inverse Tone Mapping from Low Dynamic Range Video to High Dynamic Range Displays using Convolutional Neural Networks, Asian Conference on Computer Vision (ACCV), 2018 [paper] [GitHub] [poster]
Winner of the Qualcomm Innovation Awards! Featured in an article by Electronics Times, Korea [link]
Soo Ye Kim, Munchurl Kim, A Multi-purpose Convolutional Neural Network for Simultaneous Super-resolution and High Dynamic Range Image Reconstruction, Asian Conference on Computer Vision (ACCV), 2018 [paper] [GitHub] [poster]
Hyeonjun Sim, Sehwan Ki, Jae-Seok Choi, Soo Ye Kim, Soomin Seo, Saehun Kim, Munchurl Kim, High-Resolution Image Dehazing with respect to Training Losses and Receptive Field Sizes, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018 [paper]
4th Place Award in the Image Dehazing Challenge in the NTIRE Workshop, CVPR 2018
Sehwan Ki, Hyeonjun Sim, Jae-Seok Choi, Soo Ye Kim, Soomin Seo, Saehun Kim, Munchurl Kim, Fully End-to-End learning based Conditional Boundary Equilibrium GAN with Receptive Field Sizes Enlarged for Single Ultra-High Resolution Image Dehazing, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018 [paper]
Cosmin Ancuti, Codruta O. Ancuti, Radu Timofte, Luc Van Gool, Lei Zhang, Ming-Hsuan Yang [and 59 others, including Soo Ye Kim], NTIRE 2018 Challenge on Image Dehazing: Methods and Results, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018 [paper]
Radu Timofte, Shuhang Gu, Jiqing Wu, Luc Van Gool, Lei Zhang, Ming-Hsuan Yang [and 95 others, including Soo Ye Kim], NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018 [paper]
Journals: IEEE Transactions on Image Processing
Conferences: CVPR (2025 - outstanding reviewer, 2023, 2021), ICCV (2025, 2023, 2021), ECCV (2024), NeurIPS (2025, 2021, 2020)
Rising Stars 2022, KAIST (supported by Google), 2022
Google PhD Fellowship in Machine Perception, Speech Technology and Computer Vision, Google, 2021
Outstanding Student Paper Award, Korean Institute of Broadcast and Media Engineers Fall Conference, 2020
Chaeyeon Son, Soo Ye Kim, Juyoung Kim, and Munchurl Kim, "Deep Learning based x4 and x8 Super-Resolution for Cultural Property Images".
Qualcomm-KAIST Innovation Award 2018 ($5,000 cash prize), Qualcomm, 2018
Soo Ye Kim, Dae Eun Kim, and Munchurl Kim, "ITM-CNN : Learning the Inverse Tone Mapping from Low Dynamic Range Video to High Dynamic Range Displays using Convolutional Neural Networks".
Honorable Mention Award, Image Super-Resolution Challenge, CVPR NTIRE Workshop, 2018
4th Place Award, Image Dehazing Challenge, CVPR NTIRE Workshop, 2018
KR102342526: Method and Apparatus for Video Colorization, 12.2021
KR102307622: Deep Joint Frame Processing Method and Apparatus for Performing Frame Interpolation, Super-Resolution or Inverse Tone Mapping, 09.2021
KR102238254: Method and Apparatus for Image Transformation, 04.2021
KR102221225: Method and Apparatus for Improving Image Quality, 03.2021
KR102214502: Image Joint Processing Method and Apparatus, 02.2021
KR102092205: Image Processing Method and Apparatus for Generating Super Resolution, Inverse Tone Mapping and Joint Super Resolution-Inverse Tone Mapping Processed Multiple Output Image, 03.2020
KR102083166: Image Processing Method and Apparatus, 03.2020
KR102034968: Method and Apparatus of Image Processing, 10.2019
KR101979584: Method and Apparatus for Deinterlacing, 05.2019
[06/2024] KIISE Korea Computer Congress, My Journey as a Researcher in Silicon Valley
[06/2024] KIBME Summer Conference, AI Research at Adobe: GenAI and More
[01/2024] Halla University, Introduction to Adobe Research
[09/2022] Kyung Hee University, Towards generating pixel-level details for low-level vision problems
[09/2022] Sun Moon University, Towards generating pixel-level details for low-level vision problems
[10/2019] Naver Corporation, Deep SR-ITM - ICCV 2019 oral paper
[10/2019] SK Telecom, Deep SR-ITM - ICCV 2019 oral paper
[11/2018] Samsung Electronics, Recent Trends in Inverse Tone-Mapping
Institut National des Sciences Appliquées (INSA) Lyon, Lyon, France (07. 2014 – 08. 2015)
École Active Bilingue Jeannine Manuel, Paris, France (09. 2007 – 08. 2008)
British School of Paris, Paris, France (08. 2004 – 08. 2007)
Oatlands Public School, Sydney, Australia (07. 2000 – 01. 2002)
Korean (Native)
English (Fluent)
TOEIC 990
French (Proficient)
DALF C1
Contact me via email! (sooye0404@gmail.com)