Haechang Lee

Haechang Lee

Auto-generated profile, based on publicly available information

Haechang Lee

Department of Electrical and Computer Engineering (ECE), Seoul National University, Seoul, South Korea

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 March 2025 in IEEE Access
Verified
Journal Article
Open access
HLHyunwoo Lee
Hyunwoo Lee
HLHaechang Lee
Haechang Lee
BLByung Hyun Lee
Byung Hyun Lee
SCSe Young Chun
Se Young Chun
Remote photoplethysmography (rPPG) estimation has made considerable progress by leveraging deep learning, yet its performance remains highly susceptible to the domain shifts caused by lighting, skin tone and/or movement, particularly during inference. Additionally, continuous adaptation across multiple domains is essential due to the dynamic environmental changes such as lighting transitions or continuous motions. Domain adaptation has been widely investigated mostly focusing on classification tasks with labels. Prior arts to address domain shifts in rPPG estimation, a regression task, relies on labeled data, requires pre-training on target domains, and focuses on single-domain test-time adaptation (TTA). However, there are still remaining challenges in TTA for their applicability of rPPG estimation in real-world scenarios such as no label during inference, continuous adaptation over multiple domains, and catastrophic forgetting when re-adapting to the source domain. In this work, we recast a rPPG TTA problem as a continual learning and propose an efficient continual TTA method that mitigates significant domain shifts in target domains without labels by leveraging the non-contrastive unsupervised learning loss with selectively updating only the batch normalization layers as well as alleviates catastrophic forgetting in source domain by adopting the learning without forgetting (LwF) regularization in the frequency domain. Our method without target labels consistently yielded performance improvements in challenging continual adaptation scenarios including adapting to multiple new domain datasets over several cycles. This approach does not only mitigate catastrophic forgetting in source domain, but also ensures robust performance across different domains.

5 November 2025 in Image and Vision Computing
Verified
Journal Article
Closed access
HLHaechang Lee
Haechang Lee
DMDong Ju Mun
Dong Ju Mun
HLHyunwoo Lee
Hyunwoo Lee
KLKyung Chul Lee
Kyung Chul Lee
SHSeongmin Hong
Seongmin Hong
SCSe Young Chun
Se Young Chun

15 July 2025 in IEEE Access
Verified
Journal Article
Open access
KHKi-Wook Hong
Ki-Wook Hong
MJMinhyeok Jo
Minhyeok Jo
HLHaechang Lee
Haechang Lee
SCSe Young Chun
Se Young Chun
ANAlbert No
Albert No
Recent advancements in image sensor technology have introduced non-Bayer color filter arrays (CFAs), such as Quad (2 × 2), Nona (3 × 3), and Q×Q (4 × 4) patterns, which improve performance under low-light conditions compared to the traditional Bayer CFA. Although numerous deep learning models exist for Bayer demosaicing, directly applying them to non-Bayer CFAs often yields suboptimal results, despite identical input-output dimensions and differences only in pixel-level color arrangements. In this work, we identify pixel discontinuity, a structural mismatch introduced by modern non-Bayer CFAs, as the key factor behind this performance gap. Then, based on our investigation, we propose a simple yet effective solution to mitigate it: inserting a pixel unshuffle layer at the input of existing Bayer demosaicing networks. This key operation spatially restructures the input, enabling seamless adaptation to non-Bayer patterns without altering the original network architecture. Our method significantly improves demosaicing performance with almost no increase in both network size and computational cost. Moreover, it generalizes across various CFA patterns, including Quad, Nona, and Q×Q, facilitating the reuse of Bayer-trained models for a wide range of sensor designs. Experimental results on synthetic and real non-Bayer data demonstrate the practical effectiveness of our approach, removing the need for custom model design for other non-Bayer CFA types.

30 November 2023
Verified
Conference Paper
Closed access
SPSanghoon Park
Sanghoon Park
DCDongho Choi
Dongho Choi
HLHaechang Lee
Haechang Lee
HMHanul Moon
Hanul Moon
SYSeunghyup Yoo
Seunghyup Yoo
Organic phototransistors (OPTs) are promising flexible photodetectors, but it is challenging to achieve high photosensitivity due to their intrinsic on-state current regardless of lighting conditions. In this study, photomultiplication-type organic phototransistors (PM-OPTs) are developed to suppress a dark current while producing a large photocurrent. A thin blocking layer is inserted between the source/drain electrodes and the active layer to induce a photomultiplication effect. The proposed PM-OPTs show two orders of magnitude larger photosensitivity whereas 100 times less power consumption in dark compared to conventional OPTs. We believe the proposed devices are suitable for realizing accurate and energy-efficient wearable bio-signal sensors.

9 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
JBJunseo Bang
Junseo Bang
JLJoonhee Lee
Joonhee Lee
KLKyeonghyun Lee
Kyeonghyun Lee
HLHaechang Lee
Haechang Lee
DKDong Un Kang
Dong Un Kang
SCSe Young Chun
Se Young Chun
Arbitrary-scale image super-resolution aims to upsample images to any desired resolution, offering greater flexibility than traditional fixed-scale super-resolution. Recent approaches in this domain utilize regression-based or generative models, but many of them are a single-stage upsampling process, which may be challenging to learn across a wide, continuous distribution of scaling factors. Progressive upsampling strategies have shown promise in mitigating this issue, yet their integration with diffusion models for flexible upscaling remains underexplored. Here, we present CasArbi, a novel self-cascaded diffusion framework for arbitrary-scale image super-resolution. CasArbi meets the varying scaling demands by breaking them down into smaller sequential factors and progressively enhancing the image resolution at each step with seamless transitions for arbitrary scales. Our novel coordinate-guided residual diffusion model allows for the learning of continuous image representations while enabling efficient diffusion sampling. Extensive experiments demonstrate that our CasArbi outperforms prior arts in both perceptual and distortion performance metrics across diverse arbitrary-scale super-resolution benchmarks.