Research Output

Publications

Journal articles, conference papers, and ongoing manuscripts from the CUK Computer Vision Lab.

Journal Articles Conference Papers Under Review

Journals

Journal Articles

2026 Journal

Efficient and Practical Purchase Recognition System for Unmanned Vending Machines

Geon-Ho Kim^*, Eun-Seong Kim^*, Jae-Hwan Ha, Cheol-Gwan Kim, and Keunsoo Ko

accepted to Journal of Visual Communication and Image Representation.

* Equal contributions
2026 Journal

Reference-Guided Transformer for Face Super-Resolution

Min-Yeong Kim^*, Seung-Wook Kim^*, and Keunsoo Ko

Neurocomputing, vol. 690, pp. 133824, Aug. 2026.3

* Equal contributions
2026 Journal Early Access

ET-SCS: Error-Tolerant Split Computing System for Internet of Things

Keunsoo Ko, Jaewook Lee, and Haneul Ko

IEEE Internet Computing, Early Access, Mar. 2026.
2026 Journal Early Access

Image Enhancement Based on Pigment Representation

Se-Ho Lee, Keunsoo Ko⁺, and Seung-Wook Kim

IEEE Transactions on Multimedia, Early Access, Feb. 2026.

IF 9.7 · JCR 2.7% + Corresponding author
2026 Journal

A Spatially-Aware Crowdsensing Framework for High-Fidelity 3D View Synthesis

Keunsoo Ko and Haneul Ko

IEEE Consumer Electronics Magazine, vol. 15, pp. 6-17, Mar. 2026.
2026 Journal

LUTFormer: Lookup Table Transformer for Image Enhancement

Jinwon Ko, Keunsoo Ko, Hanul Kim, and Chang-Su Kim

Neurocomputing, vol. 660, pp. 131863, Jan. 2026.
2025 Journal

A Framework for Classifying Finger Motion using Forearm Ultrasound Imaging

Yohan Lee^*, Keunsoo Ko^*, Jaeyeop Jang, Jung-Min Lee, and Changhan Yoon

Scientific Reports, vol. 15, pp. 39719, Nov. 2025.

* Equal contributions
2025 Journal

Error-Mask-Adaptive Dynamic Filtering for Image Inpainting

Keunsoo Ko, Seunggyun Woo, and Chang-Su Kim

IEEE Access, vol. 13, pp. 18403-18417, Jan. 2025.
2024 Journal

Attention-Based Hydrogen Refueling Imputation Model for Efficient Hydrogen Refueling Stations

Keunsoo Ko and Changgyun Kim

Applied Sciences, vol. 14, Nov. 2024.
2024 Journal

Local and Global Mixture Network for Image Inpainting

Seunggyun Woo, Keunsoo Ko, and Chang-Su Kim

Journal of Visual Communication and Image Representation, vol. 104, Oct. 2024.
2023 Journal

RPF: Reference-Based Progressive Face Super-Resolution Without Losing Details and Identity

Ji-Soo Kim, Keunsoo Ko, Hanul Kim, and Chang-Su Kim

IEEE Access, vol. 11, pp. 46707-46718, May. 2023.
2022 Journal

Edge-Aware Interactive Contrast Enhancement

Keunsoo Ko and Chang-Su Kim

IEEE Access, vol. 10, pp. 98981-98992, Sep. 2022.
2022 Journal

Blind and Compact Denoising Network Based on Noise Order Learning

Keunsoo Ko, Yeong Jun Koh, and Chang-Su Kim

IEEE Transactions on Image Processing, vol. 31, pp. 1657-1670, Jan. 2022.

IF 13.7 · JCR 2.0% Code
2021 Journal

Gluing Reference Patches Together for Face Super-Resolution

Ji-Soo Kim, Keunsoo Ko, and Chang-Su Kim

IEEE Access, vol. 9, pp. 169321-169334, Dec. 2021.
2021 Journal

IceNet for Interactive Contrast Enhancement

Keunsoo Ko and Chang-Su Kim

IEEE Access, vol. 9, pp. 168342-168354, Dec. 2021.

Code
2021 Journal

Light Field Super-Resolution via Adaptive Feature Remixing

Keunsoo Ko, Yeong Jun Koh, Soonkeun Chang, and Chang-Su Kim

IEEE Transactions on Image Processing, vol. 30, pp. 4114-4128, Apr. 2021.

IF 13.7 · JCR 2.0% Code
2021 Journal

Edge-Network-Assisted Real-Time Object Detection Framework for Autonomous Driving

Seung-Wook Kim, Keun-Soo Ko, Han-Eul Ko, and Victor Leung

IEEE Network, vol. 35, pp. 177-183, Feb. 2021.

IF 6.8 · JCR 9.3%

Conferences

Conference Papers

2026 Conference

Frequency-domain Manipulation for Face Obfuscation

Jintae Kim, Keunsoo Ko, and Chang-Su Kim

In CVPR, Denver, USA, Jun. 2026.

Top CS Conf. · BK IF=4 Highlight
2026 Conference

CanonCGT: Reference-Based Color Grading via Canonical Pivot Representation

Jinwon Ko, Keunsoo Ko, and Chang-Su Kim

In CVPR, Denver, USA, Jun. 2026.

Top CS Conf. · BK IF=4
2025 Conference

A User-Guided and Motion-Adaptive Framework for Virtual Product Placement in Video

Tianwen Zhang, Ju-Won Seo, Kang-Min Kim, and Keunsoo Ko

In APSIPA, Singapore, Oct. 2025.

Code
2023 Conference

Continuously Masked Transformer for Image Inpainting

Keunsoo Ko and Chang-Su Kim

In ICCV, Paris, France, Oct. 2023.

Top CS Conf. · BK IF=4 Code
2020 Conference

Adaptive Lattice-Aware Image Demosaicking Using Global and Local Information

Ji-Soo Kim, Keunsoo Ko, and Chang-Su Kim

In ICIP, Abu Dhabi, United Arab Emirates, Oct. 2020.
2020 Conference

BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation

Junheum Park, Keunsoo Ko, Chul Lee, and Chang-Su Kim

In ECCV, Glasgow, United Kingdom, Aug. 2020.

Top CS Conf. · BK IF=2 Code
2018 Conference

PAC-NET: Pairwise Aesthetic Comparison Network for Image Aesthetic Assessment

Keunsoo Ko, Jun-Tae Lee, and Chang-Su Kim

In ICIP, Athens, Greece, Oct. 2018.

Manuscripts

Under Review

Manuscripts currently under review or double-blind review.

Under Review Journal

Localization-to-Synthesis Framework for Virtual CT Angiography

Keunsoo Ko^*, Jin Young Yoo^*, Moon Hyung Choi, Kyu-Jin Jung, and Jimin Kim

Submitted to Scientific Reports.

* Equal contributions
Under Review Journal

Progressive Identity-Preserving Transformer for Reference-based Blind Face Restoration

Eun-Seong Kim^*, Min-Yeong Kim^*, and Keunsoo Ko

Submitted to IEEE Transactions on Circuits and Systems for Video Technology.

* Equal contributions
Under Review Double-blind

Face Obfuscation

Yejun So and Keunsoo Ko

Double-blind peer review.
Under Review Double-blind

Privacy-Enhancing Technology

Jintae Kim, Keunsoo Ko, and Chang-Su Kim

Double-blind peer review.

Contact

Research Collaboration

For questions about publications, code, datasets, or research collaboration, please contact the CUK Computer Vision Lab.