Bin Sun
Research Scientist at Adobe
Researcher
Builder
Startup Operator
Generative AI · Production Vision Models · Research-Driven Startups
Adobe · 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.
I am a Research Scientist at Adobe, following Adobe’s September 2026 acquisition of Topaz Labs, where I developed production AI models. My model work includes Wonder 3 / 3.5 and Recover v3, spanning image enhancement, restoration, and deployment. Earlier, I developed local generative image-editing models at Topaz and led diffusion-model 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.
I am a Research Scientist at Adobe, following Adobe’s September 2026 acquisition of Topaz Labs, where I developed production AI models. My model work includes Wonder 3 / 3.5 and Recover v3, spanning image enhancement, restoration, and deployment. Earlier, I developed local generative image-editing models at Topaz and led diffusion-model 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.
1,300+
reported research citations*
11
h-index
440+
citations on co-first-author challenge work
59
completed peer reviews (reported)
*Self-reported citation count as of September 2026; includes publications and patents. See Google Scholar for the current indexed count.
Researcher × Builder × Startup Operator
Researcher
Research depth with external validation
1,300+ reported research 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 its acquisition by Shiseido, and production AI model work at Topaz Labs through its 2026 acquisition by Adobe.
Operating principle: strong research matters most when it survives contact with real users, real hardware, and real product constraints.
Experience
Research Scientist · Adobe Topaz Labs acquisition
Sep 2026 – Present
Previously Research Scientist at Topaz Labs (2025 – Sep 2026)
Generative image enhancement, restoration, and production model ownership
- Developed and owned core model work for Wonder 3 and Wonder 3.5, production 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
- September 2026: Adobe completed its acquisition of Topaz Labs, where I work on production image models.
- August 2026: Wonder 3.5 launched; contributed core model development and ownership.
- 2025–2026: Developed production image models including Recover v3 and Wonder 3 / 3.5 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.
- Peer review: Approximately 59 completed reviews (self-reported) across conferences and journals including CVPR, ICCV, ICLR, AAAI, IJCAI, TPAMI, TIP, TCSVT, and other venues.