Bin Sun

About Me

I am a Senior Research Scientist at Picsart AI Research. My current research interests lie in Generative AI and efficient model.

I received my Ph.D degree from Electrical and Computer Engineering Department, Northeastern University, advised by Prof. Yun Fu. During my Ph.D. career, I focus on studying Computer Vision and Deep Learning, especially learning with efficient model, Face and Pose Estimation, Multi-modality, super-resolution, agriculture vision, etc. Please find the webpage of our lab here SmileLab. I have also spent time as a founding member in AI-startups (Giaran acquired by Shiseido, Ainnovationlabs). Besides, I spent three months as a computer vision engineer in Zebra. In 2023, I got a great starting stage in Topazlabs as a deep learning researcher, working on generative ai and its optimization on local devices.

News

2024.2: Start my new position of Senior Research Scientist at Picsart!
2023.11: Release the first image editing product of our company! We deploy the Stable Diffusion on local laptops.
2023.06: Goodbye Boston. Hello Dallas.
2023.05:Get an offer from TopazLabs as a Deep Learning Researcher. The topic is about Image Generation.
2023.01:One paper is accepted by ICLR as Oral.
2022.12: Defense my PhD and graduate from Northeastern University
2022.11:One paper is accepted by AAAI.
2022.03:One paper is accepted by CVPR as oral.
2021.11: One paper is accepted by IEEE TNNLS.
2021.10: Start part-time intern in Ainnovationlabs.
2021.06: Lead the team won the 4th Rank in CVPR21 Challenge on Agriculture Vision.
2021.03: Lead the team won the 1st Prize in both RGB and RGB-D tracks of CVPR21 Challenge on Large Scale Signer Independent Isolated Sign Language Recognition [code] [link] [news].
2020.11: Two papers are accepted by FG.
2020.03: One patent is filed by Zebra.
2019.06: One patent is filed by Shiseido.
2019.05: Involved in another startup Ainnovaionlabs, Inc.
2019.01: Start my internship at Zebra, Lincolnshire, IL.
2018.07: Get one paper accepted by BMVC .
2018.04: Get one paper accepted by AAAI .
2017.11: Giaran is acquired by Shiseido .
2017.01: Start my internship at Giaran as one of the founding members.
2016.09: Change my program to Ph.D .
2015.09: Begin my new journey at Northeastern University, Boston, MA.

Selected Publications [Full List and Recent Works]

Image as Set of Points
Xu Ma*, Yuqian Zhou*, Huan Wang, Can Qin, Bin Sun, Chang Liu, Yun Fu
International Conference on Learning Representations (ICLR), 2023 top 5% Oral [PDF], [Code]

Hybrid pixel-unshuffled network for lightweight image super-resolution
Bin Sun, Yulun Zhang, Songyao Jiang, Yun Fu
Association for the Advancement of Artificial Intelligence (AAAI), 2023 [PDF], [Code], [Demo]

Towards Layer-wise Image Vectorization
Xu Ma, Yuqian Zhou, Xingqian Xu, Bin Sun, Valerii Filev, Nikita Orlov, Yun Fu, Humphrey Shi
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Oral [PDF], [Code]

Visual Semantic Reasoning for Image-Text Matching

LRPRNet: Lightweight Deep Network by Low-Rank Pointwise Residual Convolution
Bin Sun, Jun Li, Ming Shao, Yun Fu
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021 [PDF], [Patent]

Skeleton aware multi-modal sign language recognition
Songyao Jiang*, Bin Sun*, Lichen Wang, Yue Bai, Kunpeng Li, Yun Fu
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW, 1st Prize), 2021 [PDF], [Code]

Ev-action: Electromyography-vision multi-modal action dataset
Lichen Wang, Bin Sun, Joseph Robinson, Taotao Jing, Yun Fu
IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2020 [PDF]

Deep Evolutionary 3D Diffusion Heat Maps for Large-pose Face Alignment
Bin Sun, Ming Shao, Siyu Xia, Yun Fu
British Machine Vision Conference (BMVC), 2018 [PDF], [Patent]

Patents

US20190014884A1 systems and Methods for Virtual Facial Makeup Removal and Simulation, Fast Facial Detection and Landmark Tracking, Reduction in Input Video Lag and Shaking, and a Method for Recommending Makeup (Granted by Shiseido)

WO2019213459A1 System and Method for Generating Image Landmarks

US11210549B2 Automated chute fullness detection (Granted by Zebra)

WO2020247545A1 Light-weight decompositional convolution neural network

WO2021163103A1 Light-weight pose estimation network with multi-scale heatmap fusion

US20230153946A1System and Method for Image Super-Resolution

Awards

4th place in CVPR21 Challenge on Agriculture Vision 2021.
1st Prize in both RGB and RGB-D tracks of CVPR21 Challenge on Large Scale Signer Independent Isolated Sign Language Recognition [code] [link] [news], 2021
Star Intern of the Year, Zebra Corp, USA, 2019.
GapFund360 Award, Northeastern University, USA, 2018.

Professonal Activities

PC Member or Reviewer for CVPR, ICCV, AAAI, IJCAI, FG, TPAMI, TIP, TCSVT, IET Image Processing, JEI, CIM