London, U.K.

The London, UK, lab is in the modern White Collar Factory building in the Shoreditch neighborhood. It is positioned on the “Silicon Roundabout” in London’s fast-growing Tech City, a hive of innovation and the third-largest technology cluster in the world after the San Francisco Bay Area and New York City. 

About us Adobe Research

AI & Machine Learning

About us Adobe Research

Computer Vision, Imaging & Video

About us Adobe Research

Content Intelligence

About us Adobe Research

Graphics (2D & 3D)

Meet some of our researchersView All

Xuelin Chen

Research Scientist

Yulia Gryaditskaya

Senior Research Scientist

Hyeonho Jeong

Research Engineer

View All

View our latest publicationsView More

Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing

Lee, Dohun., Huang, Chun-Hao., Chen, Xuelin., Ye, Jong., Ceylan, Duygu., Jeong, Hyeonho. (Sep. 12, 2026)

European Conference on Computer Vision (ECCV 2026)

EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decomposition

Hu, Yihan., Chen, Xuelin., Cun, Xiaodong. (Jun. 3, 2026)

Conference on Computer Vision and Pattern Recognition (CVPR 2026)

LoST: Level of Semantics Tokenization for 3D Shapes

Dutt, Niladri., Shi, Zifan., Guerrero, Paul., Huang, Chun-Hao., Ceylan, Duygu., Mitra, Niloy., Chen, Xuelin. (Jun. 3, 2026)

Conference on Computer Vision and Pattern Recognition (CVPR 2026)

View More

View our latest newsView All News

This World Photography Day, Adobe Research Maps How Trust Travels with a Photo

On World Photography Day, Adobe Researchers are contributing technologies that give people the information they need to understand where an image comes from, how it’s been changed, and whether its history can be independently verified.

TokenTrace at CVPR 2026: Tracing Creative Influence in Generative AI 

TokenTrace embeds lightweight watermarks into training tokens associated with visual concepts. When the model later generates an image, TokenTrace can recover traces of these watermarked signals, allowing researchers to identify which concepts most strongly contributed to the output. 

Adobe Researchers use puzzles to teach an AI model to retouch photos

Editing photos can be tricky, especially if a user isn’t familiar with all their editing tools. Adobe Researchers have developed a new AI model that spots what a user might want to fix, explains each step, and lets users choose which edits to make. Learn more about this new research!
View All News

Join us!

We are looking for researchers and interns to take our technologies to the next level. Learn about working at Adobe Research.

Learn More