About me
Hi, I am Wonhyeok Choi, a M.S.-Ph.D. integrated course student at the Department of Electrical Engineering & Computer Sciences (EECS) at DGIST, South Korea, under the supervision of Prof. Sunghoon Im in the DGIST Computer Vision Lab. My research interest is computer vision and deep learning, with a particular emphasis on solving Dynamic Neural network, Multi-task/Multi-modal learning & Meta-learning, and 3D perception tasks.
Publication
Wonhyeok Choi*, Kyumin Hwang*, Wei Peng, Minwoo Choi, Sunghoon Im. “Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining”, (ICLR), 2025. [Paper] (Under Review)
Wonhyeok Choi*, Kyumin Hwang*, Minwoo Choi, Kiljoon Han, Wonjun Choi, Mingyu Shin, Sunghoon Im. “Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces”, The Association for the Advancement of Artificial Intelligence (AAAI), 2025. [Paper] (Under Review)
Wonhyeok Choi*, Mingyu Shin*, Hyukzae Lee, Jaehoon Cho, Jaehyeon Park, Sunghoon Im. “Multi-task Learning for Real-time Autonomous Driving leveraging Task-wise Attention Generator”, IEEE International Conference on Robotics and Automation (ICRA), 2024. [Paper]
Wonhyeok Choi*, Mingyu Shin*, Sunghoon Im. “Depth-discriminative Metric Learning for Monocular 3D Object Detection”, Neural Information Processing Systems (NeurIPS), 2023. [Paper] [OpenReview]
Wonhyeok Choi, Sunghoon Im. “Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies”, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [Paper]
Seunghun Lee, Wonhyeok Choi, Changjae Kim, Minwoo Choi, Sunghoon Im. “ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation”, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [Paper]
Education
Visiting Scholar in Psychiatry and Behavioral Sciences, Stanford, USA (Aug. 2024 - Dec. 2024)
M.S - Ph.D. Integrated Course in Electrical Engineering & Computer Science (EECS), DGIST, South Korea (Mar. 2022 -)
Bachelor of Convergence Science, DGIST, South Korea (Mar. 2018 - Feb. 2022)
Hansung Science High School, South Korea (Mar. 2016 - Feb 2018)
Academic Activities
Reviewer
International Conference on Learning Representations (ICLR) 2025.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023-2024.
Conference on Neural Information Processing Systems (NeurIPS) 2024.
The European Conference on Computer Vision (ECCV) 2024.
IEEE International Conference on Robotics and Automation (ICRA) 2024.
IEEE Robotics and Automation Letters (RA-L) 2024.
IEEE International Conference on Computer Vision (ICCV) 2023.
Scholarships & Awards
Visiting Researcher, Stanford University, Sep. 2024 - Dec. 2024
Outstanding Researcher Award (디지스트 우수연구자상), Electronic Engineering & Computer Sciences (EECS), DGIST, Dec. 2023
Hwang Gyuyoung Outstanding Researcher Award (황규영 우수연구자상), Electronic Engineering & Computer Sciences (EECS), DGIST, Oct. 2023
Grand Prize, Autonomous Driving AI Development Challenge 2023, Ministry of Land, Infrastructure and Transport (국토교통부), Oct. 2023
Participation Prize, 28th HumanTech Paper Award, Samsung Electronics Co., Ltd, Feb. 2022.
Skills
Deep Learning Framework :
Pytorch★★★
Development Tools :
Python★★★
C/C++★★☆
C#★★☆
Web Development :
HTML★☆☆
CSS★☆☆
News
