Jaehyup Lee

Jaehyup Lee

Auto-generated profile, based on publicly available information

Jaehyup Lee

Kyungpook National University

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 September 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
JLJaehyup Lee
Jaehyup Lee
HCHyebin Cho
Hyebin Cho
DSDoochun Seo
Doochun Seo
HKHyun-Ho Kim
Hyun-Ho Kim
JJJaeheon Jeong
Jaeheon Jeong
MKMunchurl Kim
Munchurl Kim
Satellite Synthetic Aperture Radar (SAR) images are immensely valuable because they can be obtained regardless of weather and time conditions. However, SAR images have fatal noise and less contextual information, thus making it harder and less interpretable. So, translation of SAR to Electro-Optical (EO) images is highly required for easier interpretation. In this paper, we propose a novel coarse-to-fine context-aware SAR-to-EO image translation (CFCA-SET) framework and a misalignment-resistant loss for the misaligned pairs of SAR-EO images. With our auxiliary learning of SAR-to-Near-Infrared translation, CFCA-SET consists of a two-stage training: (i) the low-resolution SAR-to-EO translation is learned in the coarse stage via a local self-attention module that helps diminish the SAR noise, and (ii) the resulting output is used as guidance in the fine stage to generate the SAR colorization of high resolution. Our proposed auxiliary learning of SAR-to-NIR translation can successfully lead CFCA-SET to learn distinguishable characteristics of various SAR objects with less confusion in a context-aware manner. To handle the inevitable misalignment problem between SAR and EO images, we newly design a misalignment-resistant loss function. Extensive experimental results show that our CFCA-SET can generate more recognizable and understandable EO-like images compared to other methods in terms of nine image quality metrics. Our CFCA-SET surpasses the state-of-the-art methods for two (QXS and CASET) datasets with the improvements: PSNR (3.6%, 29%), ERGAS (7.4%, 30%), SSIM (15%, 15%), SAM (21%, 38%), Ds (16%, 13%), QNR (1.5%, 3.1%), CHD (18%, 12%), LPIPS (4.2%, 8%), and FID (9.0%, 33%).

19 December 2023 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
JLJaehyup Lee
Jaehyup Lee
HKHyun-Ho Kim
Hyun-Ho Kim
DSDoochun Seo
Doochun Seo
MKMunchurl Kim
Munchurl Kim
Recently, the analysis and use of Synthetic Aperture Radar (SAR) imagery have become crucial for surveillance, military operations, and environmental monitoring. A common challenge with SAR images is the presence of speckle noise, which can hinder their interpretability. To enhance the clarity of SAR images, this paper introduces a novel SAR-to-Electro-Optical (EO) image translation (SET) network, called SGCL-SET, which firstly incorporates EO object label information for stable translation. We use a pre-trained segmentation network to provide the segmentation regions with their labels into learning the SET. Our SGCL-SET can be trained to effectively learn the translation for the regions of confusing contexts by utilizing the segmentation and label information. Through comprehensive experiments on our KOMPSAT dataset, our SGCL-SET significantly outperforms all the previous methods with large margins across nine image quality evaluation metrics.

9 June 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
JDJeonghyeok Do
Jeonghyeok Do
JLJaehyup Lee
Jaehyup Lee
SLSeungchul Lee
Seungchul Lee
MKMunchurl Kim
Munchurl Kim
Synthetic Aperture Radar (SAR) imagery provides robust environmental and temporal coverage (e.g., during clouds, seasons, day-night cycles), yet its noise and unique structural patterns pose interpretation challenges, especially for non-experts. SAR-to-EO (Electro-Optical) image translation (SET) has emerged to make SAR images more perceptually interpretable. However, traditional approaches, trained from scratch on limited SAR-EO datasets, are prone to overfitting and struggle with dataset inconsistencies. To address these challenges, we introduce Confidence Diffusion for SAR-to-EO Translation (C-DiffSET), a framework leveraging a pretrained Latent Diffusion Model (LDM) to effectively adapt its extensive generative priors from natural images to the EO domain. Our investigation reveals that the pretrained VAE encoder effectively aligns SAR and EO images within a shared latent space, demonstrating robustness even to varying noise levels in SAR inputs. To further improve pixel-wise fidelity for SET and mitigate artifacts from temporal discrepancies, such as appearing or disappearing objects, we propose a novel confidence-guided diffusion (C-Diff) loss. This loss dynamically guides the diffusion process to down-weight penalties in uncertain regions, thereby enhancing structural accuracy. C-DiffSET achieves state-of-the-art (SOTA) results on multiple benchmark datasets (QXS-SAROPT, SAR2Opt, SpaceNet6, Stellar-Vision), significantly outperforming recent image-to-image translation methods and specialized SET methods across all standard metrics. The source code and trained models are available at https://github.com/KAIST-VICLab/C-DiffSET.

1 January 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
JMJaeho Moon
Jaeho Moon
JYJeonghwan Yun
Jeonghwan Yun
JKJaehyun Kim
Jaehyun Kim
JLJaehyup Lee
Jaehyup Lee
MKMunchurl Kim
Munchurl Kim

11 February 2026 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
JPJuheon Park
Juheon Park
SKSeunghyun Kim
Seunghyun Kim
MJMinyoung Jeon
Minyoung Jeon
HKHyun-Ho Kim
Hyun-Ho Kim
DSDoochun Seo
Doochun Seo
JLJaehyup Lee
Jaehyup Lee
Most existing PAN-sharpening methods assume perfect co-registration between the panchromatic (PAN) image and multispectral (MS) bands. In real-world aerial and satellite imaging, however, both PAN–MS misalignment and inter-band misalignment among MS channels frequently occur, leading to significant degradation in fusion quality. In this work, we propose RPM, a robust PAN-sharpening framework that simultaneously corrects inter-band shifts while fusing PAN and MS information. The core idea is a shift-to-align training strategy, where random band-wise shifts are introduced during training so that the network learns alignment-invariant spectral fusion guided by the PAN image. Without requiring explicitly aligned ground truth, RPM enforces spectral fidelity, spatial consistency, and robustness to inter-band misalignment. Extensive experiments on multiple benchmark datasets demonstrate that RPM consistently achieves state-of-the-art performance: on the WV3 dataset, it reduces ERGAS by up to 2–3%, lowers SAM by about 1%, and improves PSNR, SCC, HQNR, and Q8 scores by 0.1–0.2% compared with recent methods. Moreover, RPM performs inference in the millisecond range per image patch, which is over 1000× faster than prior approaches that typically require several seconds.

13 November 2025 in arXiv
Verified
Preprint
Open access
PDF file
JMJeongho Min
Jeongho Min
DKDongyoung Kim
Dongyoung Kim
JLJaehyup Lee
Jaehyup Lee
Cross-view image retrieval, particularly street-to-satellite matching, is a critical task for applications such as autonomous navigation, urban planning, and localization in GPS-denied environments. However, existing approaches often require supervised training on curated datasets and rely on panoramic or UAV-based images, which limits real-world deployment. In this paper, we present a simple yet effective cross-view image retrieval framework that leverages a pretrained vision encoder and a large language model (LLM), requiring no additional training. Given a monocular street-view image, our method extracts geographic cues through web-based image search and LLM-based location inference, generates a satellite query via geocoding API, and retrieves matching tiles using a pretrained vision encoder (e.g., DINOv2) with PCA-based whitening feature refinement. Despite using no ground-truth supervision or finetuning, our proposed method outperforms prior learning-based approaches on the benchmark dataset under zero-shot settings. Moreover, our pipeline enables automatic construction of semantically aligned street-to-satellite datasets, which is offering a scalable and cost-efficient alternative to manual annotation. All source codes will be made publicly available at https://jeonghomin.github.io/street2orbit.github.io/.