Bin Sun
AI Research Scientist · Model Builder · Startup Operator
Researcher
Builder
Startup Operator
Generative AI · Production Vision Models · Research-Driven Startups
Topaz Labs · Dallas, TX · Ph.D., Northeastern University
About
I build AI from research idea to production system. My work sits at the intersection of research, model development, productization, and startup execution: publishing highly cited computer-vision research, inventing patented technologies, deploying AI on consumer devices, and shipping commercial generative-AI models.
Today I am a Research Scientist at Topaz Labs, where I develop and own production image models including Wonder3 / Wonder3.5 and Recover v3. Previously, I built local generative image-editing models at Topaz and led Stable Diffusion-based product research at Picsart AI Research.
I also bring a startup-builder perspective. I was a founding member of Giaran, where I helped build real-time facial-analysis technology before the company was acquired by Shiseido, and I later worked with AInnovationLabs. Across these roles, I have repeatedly worked in small, research-driven teams where technical ideas had to become usable products.
I received my Ph.D. in Electrical and Computer Engineering from Northeastern University, advised by Prof. Yun Fu at SMILE Lab. My research has appeared at ICLR, CVPR, AAAI, TNNLS, BMVC, and related venues.
Today I am a Research Scientist at Topaz Labs, where I develop and own production image models including Wonder3 / Wonder3.5 and Recover v3. Previously, I built local generative image-editing models at Topaz and led Stable Diffusion-based product research at Picsart AI Research.
I also bring a startup-builder perspective. I was a founding member of Giaran, where I helped build real-time facial-analysis technology before the company was acquired by Shiseido, and I later worked with AInnovationLabs. Across these roles, I have repeatedly worked in small, research-driven teams where technical ideas had to become usable products.
I received my Ph.D. in Electrical and Computer Engineering from Northeastern University, advised by Prof. Yun Fu at SMILE Lab. My research has appeared at ICLR, CVPR, AAAI, TNNLS, BMVC, and related venues.
1,284+
Google Scholar citations
11
h-index
440+
citations on co-first-author challenge work
130+
citations on first-author AAAI work
Researcher × Builder × Startup Operator
Researcher
Research depth with external validation
1,284+ Google Scholar citations, ICLR/CVPR Oral papers, AAAI and TNNLS publications, and a CVPR challenge-winning co-first-author work.
Builder
End-to-end production model ownership
Built and shipped generative image-editing, restoration, and enhancement models including Generative Remove, Recover v3, and Wonder3 / Wonder3.5.
Startup Operator
Experience inside research-driven startups
Founding-team experience at Giaran through acquisition by Shiseido, followed by multiple startup and scale-up R&D roles bridging research and commercialization.
Operating principle: strong research matters most when it survives contact with real users, real hardware, and real product constraints.
Experience
Research Scientist · Topaz Labs
2025 – Present
Generative image enhancement, restoration, and production model ownership
- Developed and owned core model work for Wonder3 and Wonder3.5, Topaz's flagship image-enhancement models.
- Developed Recover v3 for restoration of degraded and low-quality imagery.
- Worked end-to-end across model architecture, training, evaluation, optimization, and production deployment.
Senior Research Scientist · Picsart AI Research
2024 – 2025
Generative AI and diffusion-model product research
- Led development of Stable Diffusion-based models for high-quality image generation and editing.
- Drove model research, training, and productization for production generative-AI capabilities.
Deep Learning Researcher · Topaz Labs
2023 – 2024
Generative image editing and efficient local inference
- Developed generative inpainting technology for Generative Remove.
- Optimized Stable Diffusion-style models for local inference on consumer laptops.
Startup & Early Industry Experience
2017 – 2022
- Founding member, Giaran; helped build the core real-time facial alignment / tracking technology and experienced the startup journey through acquisition by Shiseido.
- Computer Vision Engineer, Zebra Technologies; developed automated chute-fullness detection technology.
- Worked with AInnovationLabs on research-driven startup development, expanding experience across early-stage AI product building.
Selected Highlights
- 2025–2026: Developed production image models including Recover v3 and Wonder3 / Wonder3.5 at Topaz Labs.
- 2024: Joined Picsart AI Research as Senior Research Scientist and led Stable Diffusion-based product research.
- 2023: Released Topaz's local generative image-editing capability, deploying diffusion models on consumer laptops.
- 2023: Image as Set of Points accepted to ICLR as a top-5% Oral.
- 2022: Towards Layer-wise Image Vectorization accepted to CVPR as an Oral.
- 2021: Team won 1st place in both RGB and RGB-D tracks of the CVPR Sign Language Recognition Challenge.
- 2017: Giaran, where I was a founding team member, was acquired by Shiseido.
Selected Publications [Full list on Google Scholar]
Patents & Technology
- 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 Makeup Recommendation (Shiseido)
- WO2019213459A1 — System and Method for Generating Image Landmarks
- US11210549B2 — Automated Chute Fullness Detection (Zebra Technologies)
- WO2020247545A1 — Light-Weight Decompositional Convolution Neural Network
- WO2021163103A1 — Light-Weight Pose Estimation Network with Multi-Scale Heatmap Fusion
- US20230153946A1 — System and Method for Image Super-Resolution
Awards & Professional Service
- 1st Prize in both RGB and RGB-D tracks, CVPR 2021 Challenge on Large Scale Signer Independent Isolated Sign Language Recognition.
- 4th Place, CVPR 2021 Challenge on Agriculture Vision.
- Star Intern of the Year, Zebra Technologies, 2019.
- GapFund360 Award, Northeastern University, 2018.
- PC Member / Reviewer: CVPR, ICCV, AAAI, IJCAI, FG, TPAMI, TIP, TCSVT, IET Image Processing, JEI, CIM.