임성훈
Im, SunghoonDepartment of Electrical Engineering and Computer Science
학력
- 2016 ~ 2019한국과학기술원 박사
- 2014 ~ 2016한국과학기술원 석사
- 2008 ~ 2014서강대학교 학사
경력
- 2019 ~ 2019Carnegie Mellon University / Visiting Scholar
- 2018 ~ 2018Microsoft Research Asia / Research Intern
수상실적
- 2025 총장표창 / DGIST
- 2021 총장표창 / DGIST
연구실 소개
- Computer Vision Lab.
-
Research Interest: 3D reconstruction/Localization, Scene Understanding, Image/Video Synthesis, Vision for New-type Sensors
Research Interests
Related Keyword
- "Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation", Kim, Jaeyeul. (2025-04). Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation. IEEE Robotics and Automation Letters, 10(4), 3462–3469. doi: 10.1109/LRA.2025.3542327
- "A Study on the Generality of Neural Network Structures for Monocular Depth Estimation", Bae, Jinwoo. (2024-04). A Study on the Generality of Neural Network Structures for Monocular Depth Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(4), 2224–2238. doi: 10.1109/TPAMI.2023.3332407
- "자가학습과 지식증류 방법을 활용한 LiDAR 3차원 물체 탐지에서의 준지도 도메인 적응", 우정완. (2023-08). 자가학습과 지식증류 방법을 활용한 LiDAR 3차원 물체 탐지에서의 준지도 도메인 적응. 로봇학회 논문지, 18(3), 346–351. doi: 10.7746/jkros.2023.18.3.346
- "A Large-Scale Virtual Dataset and Egocentric Localization for Disaster Responses", Jeon, Hae-Gon. (2023-06). A Large-Scale Virtual Dataset and Egocentric Localization for Disaster Responses. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(6), 6766–6782. doi: 10.1109/TPAMI.2021.3094531
- "ProFeat: Unsupervised image clustering via progressive feature refinement", Kim, Jeonghoon. (2022-12). ProFeat: Unsupervised image clustering via progressive feature refinement. Pattern Recognition Letters, 164, 166–172. doi: 10.1016/j.patrec.2022.10.029
- "Style-Editor: Text-driven Object-centric Style Editing", Park, Jihun. (2025-06-14). Style-Editor: Text-driven Object-centric Style Editing. Conference on Computer Vision and Pattern Recognition (spotlight), 18281–18291.
- "Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining", Choi, Wonhyeok. (2025-04-26). Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining. International Conference on Learning Representations, 95218–95236.
- "Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces", Choi, Wonhyeok. (2025-02-28). Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces. AAAI Conference on Artificial Intelligence, 2555–2563. doi: 10.1609/aaai.v39i3.32258
- "Content-Adaptive Style Transfer: A Training-Free Approach with VQ Autoencoders", Gim, Jongmin. (2024-12-10). Content-Adaptive Style Transfer: A Training-Free Approach with VQ Autoencoders. Asian Conference on Computer Vision, 187–204. doi: 10.1007/978-981-96-0917-8_11
- "Density-aware Domain Generalization for LiDAR Semantic Segmentation", Kim, Jae-Yeul. (2024-10-16). Density-aware Domain Generalization for LiDAR Semantic Segmentation. IEEE/RSJ International Conference on Intelligent Robots and Systems, 9573–9580. doi: 10.1109/IROS58592.2024.10801829
연구 뉴스
- Development of Autonomous Driving Distance Sensing Technology That is Stable Even in Snow and Rain 2023-12-26
- Development of an accurate, low-priced core self-driving technology that recognizes the surrounding environment using 3D 2023-12-26
- DGIST Research Team Successfully Develops Multitasking AI Technology with High Accuracy and Speed 2023-12-20
- ‘값 싸고 정확하게’ 주변 환경 3D로 인식하는 자율주행 핵심 기술 개발 2023-12-19
- 눈·비 와도 ‘안정적인’자율주행 거리 센싱 기술 개발 2023-12-12
연구분야
미래유망 신기술(6T)
국가과학기술표준분류
12대 국가전략기술 분야