Hoonhee Cho

Hoonhee Cho

Ph.D. Student

I am currently pursuing my Ph.D. at Korea Advanced Institute of Science and Technology (KAIST) under the supervision of Professor Kuk-Jin Yoon.

Email: gnsgnsgml@kaist.ac.kr

Research Interests

Computer Vision and Deep Learning for Robotics, Autonomous Driving and Virtual Reality

Video & Image Enhancement

Image/Video Deblurring
Video Frame Interpolation
Video Super-resolution

Autonomous Driving

Stereo Matching, Multi-View Stereo
Semantic Segmentation, Object Detection

Event Camera

Application of Event Camera for Various Tasks

Publications

Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras

Hoonhee Cho*, Jae-Young Kang*, Youngho Kim, and Kuk-Jin Yoon

*: Equally Contributed

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025 (Highlight 3.0%)
[PDF] [Code]

Unifying Low-Resolution and High-Resolution Alignment by Event Cameras for Space-Time Video Super-Resolution

Hoonhee Cho, Jae-Young Kang, Taewoo Kim, Yuhwan Jeong, and Kuk-Jin Yoon

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025
[PDF] [Code]

A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme Conditions

Hoonhee Cho*, Taewoo Kim*, Yuhwan Jeong, and
Kuk-Jin Yoon

*: Equally Contributed

Neural Information Processing Systems (NeurIPS) 2024
Track on Datasets and Benchmarks

[PDF] [Dataset]

Temporal Event Stereo via Joint Learning with Stereoscopic Flow

Hoonhee Cho*, Jae-Young Kang*, and Kuk-Jin Yoon

*: Equally Contributed

European Conference on Computer Vision (ECCV) 2024

Finding Meaning in Points: Weakly-Supervised Semantic Segmentation for Event Cameras

Hoonhee Cho*, Sung-Hoon Yoon*, Hyeokjun Kweon*, and Kuk-Jin Yoon

*: Equally Contributed

European Conference on Computer Vision (ECCV) 2024

CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring

Taewoo Kim*, Hoonhee Cho*, and Kuk-Jin Yoon

*: Equally Contributed

European Conference on Computer Vision (ECCV) 2024

[PDF] [Code]

Towards Real-world Event-guided Low-light Video Enhancement and Deblurring

Taewoo Kim, Jaeseok Jeong, Hoonhee Cho, Yuhwan Jeong, and Kuk-Jin Yoon

European Conference on Computer Vision (ECCV) 2024

[PDF] [Code]

Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event Translation

Yuhwan Jeong*, Hoonhee Cho*, and Kuk-Jin Yoon

*: Equally Contributed

European Conference on Computer Vision (ECCV) 2024

TTA-EVF: Test-Time Adaptation for Event-based Video Frame Interpolation via Reliable Pixel and Sample Estimation

Hoonhee Cho, Taewoo Kim, Yuhwan Jeong, and Kuk-Jin Yoon

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024

Frequency-aware Event-based Video Deblurring for Real-World Motion Blur Taewoo Kim*, Hoonhee Cho*, and Kuk-Jin Yoon

*: Equally Contributed

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024

[PDF] [Project Page]

Label-Free Event-based Object Recognition via Joint Learning with Image Reconstruction from Events

Hoonhee Cho*, Hyeonseong Kim*, Yujeong Chae, and Kuk-Jin Yoon

*: Equally Contributed

International Conference on Computer Vision (ICCV) 2023 (Oral)

(Oral presentations: 1.8 %)

Non-Coaxial Event-guided Motion Deblurring with Spatial Alignment

Hoonhee Cho, Yuhwan Jeong, Taewoo Kim, and Kuk-Jin Yoon

International Conference on Computer Vision (ICCV) 2023

[PDF] [Project Page]

Learning Adaptive Dense Event Stereo from the Image Domain

Hoonhee Cho, Jegyeong Cho, and Kuk-Jin Yoon

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

Efficient Reference-based Video Super-Resolution (ERVSR): Single Reference Image Is All You Need

Youngrae Kim*, Jinsu Lim*, Hoonhee Cho*, Minji Lee*, Dongman Lee, Ho-Jin Choi, and Kuk-Jin Yoon

*: Equally Contributed

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023)

Selection and Cross Similarity for Event-Image Deep Stereo

Hoonhee Cho and Kuk-Jin Yoon

European Conference on Computer Vision (ECCV 2022)

Event-image Fusion Stereo using Cross-modality Feature Propagation

Hoonhee Cho and Kuk-Jin Yoon

Thirty-Six AAAI Conferecne on Artificial Intelligence (AAAI 2022)

[PDF] [Dataset]

EOMVS : Event-based Omnidirectional Multi-View Stereo

Hoonhee Cho, Jaeseok Jeong, and Kuk-Jin Yoon

IEEE Robotics and Automation Letters (2021) with IROS

Experiences

2022.03 - ing: Ph.D. student, Robotics, KAIST
2020.09 - 2022.02: MS. student, Robotics, KAIST
2016.03 - 2020.08: Undergraduate student, Mechanical Enginerering, KAIST

Honors & News

IEEE SPECTRUM News August 2021

Event-based Omnidirectional Multi-view Stereo (EOMVS) was introduced in IEEE Spectrum, with the title “This Camera Can “See” the Bigger Picture: Researchers’ new camera spots fast-moving objects over a wide angle of view“. https://spectrum.ieee.org/new-camera-sees-more

Vision Systems Design Main News November 2021

Event-based Omnidirectional Multi-view Stereo (EOMVS) was introduced in vision systems design main news. https://www.vision-systems.com/non-factory/article/14212132/multiview-stereo-method-uses-eventbased-omnidirectional-imaging

Mohamed Bin Zayed International Robotics Challenge (MBZIRC) Final Team December 2022

The Mohamed Bin Zayed International Robotics Challenge (MBZIRC) aims to be one of the world’s largest and most prestigious international robotics competitions. https://www.mbzirc.com

Academic Service

I have been serving the research community as reviewers

2021 IEEE Transactions on Instrumentation & Measurement

2023 Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI)

2023 International Conference on Computer Vision (ICCV)

2024 Thirty-Eight AAAI Conference on Artificial Intelligence (AAAI)

2024 IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)

2024 IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

2024 European Conference on Computer Vision (ECCV)

Page updated

Google Sites

Report abuse