Bang-Dang Pham

I am a second-year PhD student at the University of Wisconsin–Madison. Previously, I was an AI Research Resident supervised by Prof. Minh Hoai, Prof. Cuong Pham, and Dr. Tuan Anh Tran at VinAI Research, Vietnam. In Summer 2025, I interned at Sony R&D Lab, working on gallery-based image restoration.

I received my B.Sc. in Computer Science from Ho Chi Minh City University of Science (HCMUS) under the supervision of Dr. Ngoc-Thao Nguyen and Prof. Minh-Triet Tran.

My research interests include Generative Models, 3D Reconstruction, and Image Restoration.

Email  /  CV  /  GitHub  /  Scholar  /  LinkedIn

🏆   [Feb 2026]   BluRef accepted to CVPR 2026.

💼   [May 2025]   Joined Sony R&D as a Research Intern, working on gallery-based image restoration.

🎓   [Aug 2024]   Started my PhD at University of Wisconsin–Madison.

🏆   [Feb 2024]   Blur2Blur accepted to CVPR 2024.

🏆   [Feb 2023]   HyperCUT accepted to CVPR 2023.

🏅   [Dec 2022]   Received Excellent B.Sc. in Computer Science (top 1%, GPA: 3.9/4.0) from HCMUS.

🔬   [Jul 2022]   Joined VinAI Research, Vietnam as a Research Resident.

• Research Intern at Sony R&D Lab
Developed methods for gallery-based image restoration, with a focus on reference-based pipelines and real-world deployment.
Mentor: Owen Mayer and Anish Lahiri

May 2025 – Aug 2025

• AI Research Resident at Qualcomm AI Research (formerly VinAI Research)
Worked on Unsupervised Image Deblurring and Generative Models
Mentor: Prof. Minh Hoai, Prof. Cuong Pham and Anh Tran

Jul 2022 – Aug 2024

Introduces a novel unpaired reference-based deblurring framework for camera-specific image restoration, eliminating the need for controlled data collection or paired supervision. The method leverages an iterative dense-matching training strategy to construct high-quality pseudo ground truth, enabling robust generalization across diverse real-world blur scenarios.

Introduces a novel framework to train camera-specific image deblurring algorithms by transforming challenging real blurry images into known blur kernels using only unpaired data, simplifying the deblurring process and demonstrating superior performance on benchmarks.

Tackles image-to-video deblurring, resolving sequence order ambiguity using a self-supervised method. Also introduces a diverse real blur-to-video image dataset (RB2V) covering domains like faces, hands, and streets.

• CS Departmental Scholarship, University of Wisconsin–Madison.
• 1st Prize in SHREC’22 Track: Open-Set 3D Object Retrieval – 2022.
• Distinctive Mention in MediaEval 2021 Workshop Program – 2021.
• 1st Prize in Visual Sentiment Analysis of MediaEval 2021.
• 1st Prize in 3D Shape Retrieval Challenge (SHREC’21) – 2021.
• 1st Prize in Sports Video Classification of MediaEval 2020.
• Excellent Young Research Award at VANJ 2020 Conference – 2020.
• Top 10 at AI4VN – 2020.
• Top 3 at Emotion Recognition Competition – 2019.
• Top 5 at Zalo AI Hackathon – 2019.
• 2nd Prize in Informatics Olympic Contest for Students – 2019.
• 2nd Prize in National Master of Ceremonies Contest – 2019.
• 3rd Prize in Informatics Olympic Contest for Students – 2018.

• Conferences: CVPR, ICCV, ECCV, NeurIPS, ACM MM, WACV (2024–2025)
• Journals: IEEE TPAMI, IJCV, CVIU, Pattern Recognition, Neural Networks (2024–2025)

Template from Jon Barron