Wooseok Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Wooseok Lee has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
Ahyoun Choi
Interdisciplinary Program for Bioengineering, Seoul National University, Seoul 08826, South Korea
1 shared publication- Amos Chungwon Lee
Bio-MAX Institute, Seoul National University, Seoul, Republic of Korea
1 shared publication - Dong-Guk Park
Department of Surgery, Dankook University Hospital, Dankook University College of Medicine, Cheonan, Korea
1 shared publication Dong-Hun Kang
Department of Electrical Engineering, Myongji University, Yongin, South Korea
1 shared publication- Il-Oun Lee
Department of Electrical Engineering, Myongji University, Yongin, Republic of Korea
1 shared publication - Jiyun Kim
School of Materials Science and Engineering Ulsan National Institute of Science and Technology Ulsan 44919 South Korea
1 shared publication
Latest Publications
- Open Access
AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network
Blind-spot network (BSN) and its variants have made significant advances in self-supervised denoising. Nevertheless, they are still bound to synthetic noisy inputs due to less practical assumptions like pixel-wise independent noise. Hence, it is challenging to deal with spatially correlated real-world noise using self-supervised BSN. Recently, pixel-shuffle downsampling (PD) has been proposed to remove the spatial correlation of real-world noise. However, it is not trivial to integrate PD and BSN directly, which prevents the fully self-supervised denoising model on real-world images. We propose an Asymmetric PD (AP) to address this issue, which introduces different PD stride factors for training and inference. We systematically demonstrate that the proposed AP can resolve inherent trade-offs caused by specific PD stride factors and make BSN applicable to practical scenarios. To this end, we develop AP-BSN, a state-of-the-art self-supervised denoising method for real-world sRGB images. We further propose random-replacing refinement, which significantly improves the performance of our AP-BSN without any additional parameters. Extensive studies demonstrate that our method outperforms the other self-supervised and even unpaired denoising methods by a large margin, without using any additional knowledge, e.g., noise level, regarding the underlying unknown noise.
Open AccessAP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network
Blind-spot network (BSN) and its variants have made significant advances in self-supervised denoising. Nevertheless, they are still bound to synthetic noisy inputs due to less practical assumptions like pixel-wise independent noise. Hence, it is challenging to deal with spatially correlated real-world noise using self-supervised BSN. Recently, pixel-shuffle downsampling (PD) has been proposed to remove the spatial correlation of real-world noise. However, it is not trivial to integrate PD and BSN directly, which prevents the fully self-supervised denoising model on real-world images. We propose an Asymmetric PD (AP) to address this issue, which introduces different PD stride factors for training and inference. We systematically demonstrate that the proposed AP can resolve inherent trade-offs caused by specific PD stride factors and make BSN applicable to practical scenarios. To this end, we develop AP-BSN, a state-of-the-art self-supervised denoising method for real-world sRGB images. We further propose random-replacing refinement, which significantly improves the performance of our AP-BSN without any additional parameters. Extensive studies demonstrate that our method outperforms the other self-supervised and even unpaired denoising methods by a large margin, without using any additional knowledge, e.g., noise level, regarding the underlying unknown noise.
- Open Access
- 26 March 2021
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 7 (13) , eabf3804
Direct 2D-to-3D transformation of pen drawings
Technology for transforming a 2D pen drawing into a designed 3D structure enables highly accessible, rapid 3D fabrication.
- 26 March 2021
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 7 (13) , eabf3804
Open AccessDirect 2D-to-3D transformation of pen drawings
Technology for transforming a 2D pen drawing into a designed 3D structure enables highly accessible, rapid 3D fabrication.
- 20 May 2020
- Published by Springer Nature in Journal of Power Electronics
- Vol. 20 (4) , 1076-1087
Torch motor control algorithm for low spatter CO2 arc welding of ultra-thin steel sheets
- 20 May 2020
- Published by Springer Nature in Journal of Power Electronics
- Vol. 20 (4) , 1076-1087
Torch motor control algorithm for low spatter CO2 arc welding of ultra-thin steel sheets
- Open Access
- 1 January 2019
- Vol. 42 (1) , 87-95
Novel Discovery of LINE-1 in a Korean Individual by a Target Enrichment Method
Wonseok Shin, Seyoung Mun, Junse Kim, Wooseok Lee, Dong-Guk Park, Seungkyu Choi, Tae Yoon Lee, Seunghee Cha, and Kyudong Han. Mol. Cells 2019;42:87-95. https://doi.org/10.14348/molcells.2018.0351
- 1 January 2019
- Vol. 42 (1) , 87-95
Open AccessNovel Discovery of LINE-1 in a Korean Individual by a Target Enrichment Method
Wonseok Shin, Seyoung Mun, Junse Kim, Wooseok Lee, Dong-Guk Park, Seungkyu Choi, Tae Yoon Lee, Seunghee Cha, and Kyudong Han. Mol. Cells 2019;42:87-95. https://doi.org/10.14348/molcells.2018.0351