πŸ§β€β™‚οΈ Biography

I received my B.S. degree in 2023 from the Department of Statistics and Information Science at Fu Jen Catholic University (FJCU), Taiwan, where I was advised by Prof. Hao-Chiang Shao. I completed my M.S. degree in 2025 at National Cheng Kung University (NCKU), where I conducted research at the Advanced Computer Vision Laboratory (ACVLAB) under the mentorship of Prof. Chih-Chung Hsu and the Computational Photography Laboratory (CPLAB) at National Yang Ming Chiao Tung University (NYCU), working with Prof. Yu-Lun Liu. I will be pursuing my Ph.D. at the University at Albany, State University of New York (SUNY Albany), where I will conduct research at the Computer Vision and Machine Learning Laboratory (CVML LAB) under the co-supervision of Prof. Ming-Ching Chang and Prof. Xin Li.

Find my resume here (last updated Jan 17, 2026).

My research interests include, but are not limited to, Low-level Vision Problems, Computational Photography, Hyperspectral Image Processing, Multimedia Analysis and Security, Efficient AI and Model Acceleration, and Medical Image Analysis.

I am always open to research collaborations. If you are interested in working together or simply want to exchange ideas, please feel free to reach out to me via email.

In my free time, I enjoy traveling ✈️, capturing moments through photography πŸ“Έ, and making desserts 🍰.

πŸ“’ News & Achievements

Filter:
2026.04.30 [ICIP] One paper accepted by ICIP.
2026.04.28 [JSTARS] One paper accepted by JSTARS.
2026.03.24 [CVPRW] Two paper accepted by CVPR Workshops (CV4Edu and NTIRE).
2026.03.21 [Top 1%] Top 1% (5/258) performance in CVPR 2026, NTIRE Bokeh Rendering Challenge.
2026.03.20 [Top 1%] Top 1% (5/569) performance in CVPR 2026, NTIRE Image Super-resolution Challenge.
2026.03.19 [Top 1%] Top 1% (6/5268) performance in CVPR 2026, NTIRE Robust Deepfake Detection Challenge.
2026.03.18 [3rd Place] 3rd in CVPR 2026, NTIRE Ambient Lighening Normalization Challenge.
2026.03.14 [Top 2%] Top 2% performance in CVPR 2026, PBVS Mars Landslide Segmentation Challenge.
2026.02.21 [CVPR] Three paper accepted by CVPR and CVPR Findings.
2026.01.29 [TGRS] One paper accepted by TGRS.
2026.01.18 [ICASSP] Two papers accepted by ICASSP 2026.
2025.12.23 πŸͺ– Started military service.
2025.12.17 [Winner] 1st performance in WACV 2026, SkiTB Visual Tracking Challenge.
2025.12.03 [3rd Place] 3rd performance in ICASSP 2026, Hyper-Object Challenge (Spectral Reconstruction & Super-Resolution).
2025.11.24 [Top 2%] Top 2% performance in BMVC 2025, Data-Centric Land Cover Classification Challenge.
2025.11.17 [IJCV] One paper accepted by IJCV.
2025.11.14 [WACV] One paper accepted by WACV 2026.
2025.10.23 [Best Thesis] Best Master Thesis Award in IEEE Tainan Section 2025. Link
2025.09.19 [Award] Future Tech Awards (2025 ζœͺδΎ†η§‘ζŠ€ηŽ) (Top-3%).
2025.08.20 [Award] Excellent Master Thesis Award (IPPR 2025) & Best Paper Award (CVGIP 2025). Link
2025.07.24 [ICCVW] One paper accepted by ICCVW 2025.
2025.07.19 [ACMMM] Three papers accepted by ACMMM 2025.
2025.07.15 [Winner] 1st performance in ACMMM 2025, SoccerTrack Challenge@MMSports.
2025.07.07 πŸŽ‰ Successfully defended Master's Thesis in NCKU!
2025.07.06 [Winner] 1st performance in ICCV 2025, Multi-source COV19 Detection Challenge.
2025.06.18 [Top 2%] Top 2% ranking in ACMMM 2025, Social Media Popularity Prediction Challenge.
2025.05.30 [Winner] 1st performance in ICRA 2025, TreeScope Tree Diameter Estimation Challenge.
2025.03.24 [3rd Place] 3rd performance in CVPR 2025, NTIRE Workshop, Image Shadow Removal Challenge.
2025.03.24 [Top 3%] Top 3% ranking in CVPR 2025, NTIRE Workshop, Image Reflection Removal Challenge.
2025.03.15 [IGARSS] Four papers accepted by IGARSS 2025.
2024.12.24 [Runner-up] Runner-up in WACV 2025, USV-based Embedded Obstacle Segmentation Challenge.
2024.09.19 [Award] Future Tech Awards (2024 ζœͺδΎ†η§‘ζŠ€ηŽ). Link
2024.07.01 [Winner] Winner in ICPR 2024, Beyond Visible Spectrum: AI for Agriculture Challenge.
2024.05.01 [Award] Top Performance Award in ACMMM 2024, Social Media Popularity Prediction Challenge.
2024.03.24 [3rd Place] 3rd place in CVPRW 2024, COVID-19 Detection Challenge.
2024.03.24 [6th Place] 6th place in CVPRW, NTIRE 2024 Image Super-Resolution (x4).
2023.11.01 [Gold Medal] Gold Medal Award (1/150+) in SAS Hackathon.
2023.10.01 [Jury Prize] Jury Prize (1/176) in ICCV 2023, Visual Inductive Priors Workshop Instance Segmentation Challenge.
2023.06.01 [Winner] Winner in ICASSP 2023, COV19 Detection Challenge.
Filter by Topic:
Under Review

SimFlowSR: Consistent Information Flow with Self-similarity Aggregation for Single Image Super-Resolution

Chia-Ming Lee, Chih-Chung Hsu

About

Recovers fine image details by aggregating recurring self-similar patterns across the image while maintaining consistent information flow through the network, preventing useful texture signals from fading in deep layers.

CVPR 2026

PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors

Chia-Ming Lee, Yu-Fan Lin, Yu-Jou Hsiao, Jin-Hui Jiang, Yu-Lun Liu, Chih-Chung Hsu

About Github Stars

Removes shadows from images by incorporating physical light models and geometric priors, enabling robust restoration across diverse real-world scenes and lighting conditions without retraining for each domain.

CVPR 2026

ReflexSplit: Single Image Reflection Separation via Layer Fusion–Separation

Chia-Ming Lee, Yu-Fan Lin, Jin-Hui Jiang, Yu-Jou Hsiao, Chih-Chung Hsu, Yu-Lun Liu

About Github Stars

Separates reflected and transmitted layers in a single photo by alternating between fusing and splitting mixed features, teaching the network to disentangle overlapping visual signals that are hard to distinguish.

WACV 2026

WWE-UIE: A Wavelet & White Balance Efficient Network for Underwater Image Enhancement

Ching-Heng Cheng, Jen-Wei Lee, Chia-Ming Lee, Chih-Chung Hsu

About Github Stars

Enhances murky underwater photos by combining wavelet-based frequency analysis with white balance correction, efficiently restoring natural colors and recovering details lost to water scattering.

ACMMM 2025

DenseSR: Image Shadow Removal as Dense Prediction

Yu-Fan Lin, Chia-Ming Lee, Chih-Chung Hsu

About Github Stars

Reframes shadow removal as a per-pixel dense prediction task, allowing the model to jointly estimate shadow regions and restore the underlying colors in a single unified pass.

CVPRW 2024

DRCT: Saving Image Super-Resolution away from Information Bottleneck

Chih-Chung Hsu, Chia-Ming Lee, Yi-Shiuan Chou

About Github Stars

Keeps high-frequency image details alive throughout the super-resolution process by introducing dense residual connections in a transformer backbone, preventing fine textures from being discarded in deep layers.

TGRS 2026

PromptHSI: Universal Hyperspectral Image Restoration with Vision-Language Modulated Frequency Adaptation

Chia-Ming Lee, Ching-Heng Cheng, Yu-Fan Lin, Yi-Ching Cheng, Wo-Ting Liao, Chih-Chung Hsu, Fu-En Yang, Yu-Chiang Frank Wang

About Github Stars

Restores degraded hyperspectral images using text prompts to guide frequency-domain adaptation, allowing a single model to handle multiple types of noise and distortion without task-specific retraining.

ICASSP 2026

HSSDCT: Factorized Spatial-Spectral Correlation for Hyperspectral Image Fusion

Chia-Ming Lee, Yu-How He, Yu-Fan Lin, Jen-Wei Lee, Chih-Chung Hsu, Li-Wei Kang

About

Fuses low-resolution hyperspectral and high-resolution RGB images by factorizing spatial and spectral correlations separately, producing sharp, spectrally accurate results with reduced computational cost.

Submitted to TGRS

AuroraHSI: An End-to-End Hyperspectral Image Fusion Method for Degraded Imagery

Chia-Ming Lee, Cheng-Jun Kang, Ching-Heng Cheng, Yu-Fan Lin, Yi-Shiuan Chou, Chih-Chung Hsu, Fu-En Yang, Yu-Chiang Frank Wang

About

An end-to-end pipeline that simultaneously denoises and fuses degraded hyperspectral imagery, recovering both spatial sharpness and spectral fidelity even when the input is corrupted by multiple types of real-world noise.

JSTARS 2026

S3RNet: Sparse Spatial-Spectral Representation with Hybrid Knowledge Distillation for Efficient Hyperspectral Image Pansharpening

Chia-Ming Lee, Yu-Fan Lin, Li-Wei Kang, Chih-Chung Hsu

About

Sharpens hyperspectral images efficiently by using sparse representations to capture the most informative spatial-spectral patterns, while knowledge distillation from a larger teacher model compensates for the reduced capacity.

IGARSS 2025

Robust Hyperspectral Image Pansharpening via Sparse Spatial-Spectral Representation

Chia-Ming Lee, Yu-Fan Lin, Li-Wei Kang, Chih-Chung Hsu

About

Enhances the spatial resolution of hyperspectral images by learning sparse representations that capture the most salient spatial and spectral features, maintaining robustness against noise and misalignment.

IGARSS 2025

HyperForensics++: Toward Adversarial Perturbed and Object Replacement in Hyperspectral Imaging Dataset

Chih-Chung Hsu, Chia-Ming Lee, Yu-Fan Lin, Min-Zo Ko, En-Zhao Liu, Yi-Ching Cheng, Ming-Ching Chang

About

Introduces a benchmark dataset and detection framework for hyperspectral image forensics, targeting adversarial perturbations and object replacement attacks that are invisible in RGB but detectable across spectral bands.

IGARSS 2025

HyFusion: Enhanced Reception Field Transformer for Hyperspectral Image Fusion

Chia-Ming Lee, Yu-Fan Lin, Yu-Hao Ho, Chih-Chung Hsu, Li-Wei Kang

About

Improves hyperspectral image fusion by enlarging the transformer's receptive field, enabling the model to capture long-range spatial dependencies that are critical for preserving fine structural details in the fused output.

TGRS 2024

Real-Time Compressed Sensing for Joint Hyperspectral Image Transmission and Restoration for CubeSat

Chih-Chung Hsu, Chih-Yu Jian, Eng-Shen Tu, Chia-Ming Lee, Guan-Lin Chen

About Github Stars

Enables tiny CubeSat satellites to transmit hyperspectral data in real time by compressing imagery on-board via compressed sensing and jointly restoring it on the ground, trading bandwidth for fidelity under strict power constraints.

CVPR Findings 2026

ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers

Chih-Chung Hsu, Xin-Di Ma, Wo-Ting Liao, Chia-Ming Lee

About

Speeds up vision transformers by replacing the standard quadratic attention with a hardware-friendly linear scan, achieving the same exact results at a fraction of the memory and compute cost β€” with no approximation involved.

Under Review

FracQuant: Fractal Complexity Assessment for Content-aware Image Super-resolution Network Quantization

Chia-Ming Lee, Yu-Fan Lin, Fu-En Yang, Yu-Chiang Frank Wang, Chih-Chung Hsu

About

Compresses super-resolution networks more intelligently by measuring the fractal complexity of each image region, allocating higher precision where detail matters and lower precision where the content is simple.

IJCV 2026

UMCL: Unimodal-generated Multimodal Contrastive Learning for Cross-compression-rate Deepfake Detection

Ching-Yi Lai, Chih-Yu Jian, Pei-Cheng Chuang, Chia-Ming Lee, Chih-Chung Hsu, Chiou-Ting Hsu, Chia-Wen Lin

About

Detects deepfakes robustly across different video compression levels by synthesizing multimodal training signals from a single modality, using contrastive learning to keep real and fake representations well-separated even when compression artifacts obscure subtle forgery traces.

Submitted to TIFS

Towards Robust DeepFake Detection under Unstable Face Sequences: Adaptive Sparse Graph Embedding with Order-Free Representation and Explicit Laplacian Spectral Prior

Chih-Chung Hsu, Shao-Ning Chen, Mei-Hsuan Wu, Chia-Ming Lee, Yi-Fang Wang, Yi-Shiuan Chou

About

Detects deepfakes in low-quality or temporally inconsistent video sequences by modeling facial dynamics as sparse graphs, using order-free representations and spectral graph priors to stay robust against missing frames and heavy compression.

ACMMM 2025

Anchoring Trends: Mitigating Social Media Popularity Prediction Drift via Feature Clustering and Expansion

Chia-Ming Lee, Bo-Cheng Qiu, Cheng-Jun Kang, Yi-Hsuan Wu, Jun-Lin Chen, Yu-Fan Lin, Yi-Shiuan Chou, Chih-Chung Hsu

About

Addresses prediction drift in social media popularity models by anchoring features to stable trend clusters and using LLM-guided expansion to enrich representations, keeping forecasts accurate as content trends shift over time.

ACMMM 2024

Revisiting Vision-Language Features Adaptation and Inconsistency for Social Media Popularity Prediction

Chih-Chung Hsu, Chia-Ming Lee, Yu-Fan Lin, Yi-Shiuan Chou, Chi-Han Tsai

About

Predicts social media post popularity by identifying and resolving inconsistencies between visual and language features, using cross-modal adaptation to better capture what makes content resonate with audiences.

ACMMM 2023

Gradient Boost Tree Network based on Extensive Feature Analysis for Popularity Prediction of Social Posts

Chih-Chung Hsu, Chia-Ming Lee, Xiu-Yu Hou, Chi-Han Tsai

About

Forecasts social post popularity by combining gradient boosted trees with an extensive set of handcrafted visual, textual, and temporal features, providing strong interpretable baselines for multimodal popularity prediction.

Under Review

DSSFT: Dense Spatial-Slice Fusion Transformer for Medical Volumetric Super-Resolution

I-An Tsai, Chia-Ming Lee, Shen-Chieh Tai, Chun-Rong Huang, Chih-Chung Hsu

About

Upscales low-resolution 3D medical scans (e.g., MRI/CT) by densely fusing spatial and slice-wise features across the volume, recovering fine anatomical details that are critical for accurate clinical diagnosis.

ICCVW 2025

Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization

Chia-Ming Lee, Bo-Cheng Qiu, Ting-Yao Chen, Ming-Han Sun, Fang-Ying Lin, Jung-Tse Tsai, I-An Tsai, Chih-Chung Hsu

About

Improves COVID-19 detection across CT scans from different hospitals by standardizing inputs at the image level before they enter the model, reducing domain gap without requiring access to target domain labels.

CVPRW 2024

A Closer Look at Spatial-Slice Features Learning for COVID-19 Detection

Chih-Chung Hsu, Chia-Ming Lee, Yang Fan Chiang, Yi-Shiuan Chou, Chih-Yu Jiang, Shen-Chieh Tai, Chi-Han Tsai

About

Detects COVID-19 in CT scans by jointly learning spatial features within each slice and inter-slice features across the volume, using morphological analysis to focus attention on clinically relevant lung regions.

arxiv 2024

Divide and Conquer: Grounding a Bleeding Areas in Gastrointestinal Image with Two-Stage Model

Yu-Fan Lin, Bo-Cheng Qiu, Chia-Ming Lee, Chih-Chung Hsu

About

Locates bleeding regions in gastrointestinal endoscopy images using a two-stage pipeline that first detects candidate areas and then precisely segments them, improving sensitivity for small or subtle lesions.

ICASSPW 2023

Bag of Tricks of Hybrid Network for Covid-19 Detection of CT Scans

Chih-Chung Hsu, Chih-Yu Jian, Chia-Ming Lee, Chi-Han Tsai, Shen-Chieh Tai

About

Diagnoses COVID-19 from CT scans by combining CNN and transformer branches in a hybrid network, augmented with a collection of training and inference tricks (augmentation, test-time ensembling, etc.) to maximize detection accuracy.

ACMMM 2025

GTATrack: Winner Solution to SoccerTrack 2025 with Deep-EIoU and Global Tracklet Association

Rong-Lin Jian, Ming-Chi Luo, Cheng-Wei Huang, Chia-Ming Lee, Yu-Fan Lin, Chih-Chung Hsu

About

Tracks soccer players in fisheye video by combining an improved IoU-based detector with a global tracklet association strategy, handling severe occlusion and wide-angle distortion to achieve winning performance at SoccerTrack 2025.

MIPR 2024

OmniDet: Omnidirectional Object Detection via Fisheye Camera Adaptation

Chih-Chung Hsu, Wei-Hao Huang, Wen-Hai Tseng, Ming-Hsuan Wu, Ren-Jung Xu, Chia-Ming Lee

About

Adapts standard object detectors to handle the extreme radial distortion of fisheye cameras, enabling reliable 360Β° omnidirectional detection without requiring purpose-built hardware or full dataset re-annotation.

ICCVW 2023

MISS: Memory-efficient Instance Segmentation Framework By Visual Inductive Priors Flow Propagation

Chih-Chung Hsu, Chia-Ming Lee

About

Performs instance segmentation with low memory overhead by propagating visual inductive priors across frames, enabling accurate object masking even under a few-shot setting without storing large feature maps.

MMAsia 2023

Adapting Object Detection to Fisheye Cameras: A Knowledge Distillation with Semi-Pseudo-Label Approach

Chih-Chung Hsu, Wen-Hai Tseng, Ming-Husan Wu, Chia-Ming Lee, Wei-Hao Huang

About

Adapts pretrained object detectors to fisheye cameras using a combination of knowledge distillation and semi-supervised pseudo-labels, reducing the need for expensive fisheye-specific annotations.

APCCAS 2025

OCR is All you need: Importing Multi-Modality into Image-based Defect Classification System

Chih-Chung Hsu, Chia-Ming Lee, Po-Tsun Yu, Chun-Hung Sun, Kuang-Ming Wu

About

Enriches image-based defect classification by extracting text from product labels via OCR and fusing it with visual features, allowing the model to leverage both appearance and specification information for more accurate industrial defect detection.