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.

100 Patents: Brian Price on innovating at Adobe Research 

Every day, Adobe researchers push the boundaries of technology—a process that’s second nature to Principal Scientist Brian Price. Price has now contributed to his 100th patent at Adobe. We talked with him about his work.

Summit Sneak winner Project Face Off: AI personas with an attitude 

Learn the behind-the-scenes story of Project Face Off - voted the best Summit Sneak of the year. 

Do it for me, or show me how: The research behind Photoshop’s AI Assistant

Adobe Research has helped build an AI Assistant for Photoshop that lets you edit images by simply describing what you want.

Adobe Firefly’s alt text: Helping blind and low-vision creators design and choose images

A new feature in Adobe Firefly built in collaboration with Adobe Research is making text-to-image generation more accessible for blind and low-vision (BLV) creators.

Teaching an AI Agent to Retouch Photos: RetouchIQ at CVPR 2026

RetouchIQ is an experimental AI editing agent that understands what you mean when you describe how a photo should look and feel, then translates that intent into precise adjustments in professional photo-editing software. 

CVPR 2026: Adobe researchers present 75+ papers on the frontier of AI

Adobe Researchers are helping shape the future of AI at the world’s premiere computer vision event, CVPR 2026, the IEEE/CVR Computer Vision and Pattern Recognition Conference. Adobe Researchers are presenting over 75 research papers, including several Oral Papers and award finalists.

A Single Primitive to Rule Them All: SuperFit at CVPR 2026 Compresses 3D Shapes into Editable Building Blocks  

SuperFit - presented at CVPR 2026 - converts complex 3D shapes into compact assemblies of simple, interpretable building blocks, called SuperFrusta. 

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.