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!

A first look at Adobe Research’s SIGGRAPH 2025 papers

Catch a preview of Adobe Research’s publications at SIGGRAPH 2025 in this new trailer, featuring innovations in video editing, 3D reconstruction, image transformation and more. With 25 total papers this year, explore the list and find us at the conference to see what’s next in creative tech.

Adobe Research advances Agentic AI

From helping create the Acrobat AI Assistant to the AEP AI Assistant, Adobe Research is pioneering agentic AI to superpower creativity and productivity. See how our latest breakthroughs are shaping what’s next and explore the key initiatives in our work on agentic AI.

The Story of Project Dub Dub Dub: From Adobe MAX Sneak to cutting-edge AI translation tool inside Adobe Firefly 

First introduced as Project Dub Dub Dub at Adobe MAX 2023, this AI tech now powers the cutting-edge translation tool in Adobe Firefly. It translates videos while matching the speaker’s voice, tone, and cadence. Explore the tech behind the magic!

Adobe Researcher brings a scientific perspective to UK policymakers tackling disinformation and deepfakes

This spring, John Collomosse, Sr. Principal Scientist at Adobe Research, joined the Royal Society’s prestigious Pairing Scheme in Westminster to share his expertise in content authenticity with UK policymakers.

Adobe Research’s Valentin Deschaintre takes home the Eurographics Young Researcher Award

Adobe Research Scientist Valentin Deschaintre has received the prestigious 2025 Eurographics Young Researcher Award for his outstanding work at the intersection of computer graphics and computer vision. Read the full story to learn more about his research, its impact on Adobe users, and more!

Adobe Researchers present a powerful, unified approach to generative video editing at CVPR 2025

Adobe researchers shared a groundbreaking paper at CVPR 2025, introducing an experimental generative video propagation framework that applies edits in the first frame of a video to all the following frames in a reliable and consistent manner, all while preserving areas the user hasn’t edited.

Adobe Research at CHI: An experimental new design approach for human-AI co-creation

To go beyond simple AI prompts and outputs, Adobe Researchers, in a paper presented at CHI 2025, outlined a new approach for designing environments where humans and AI can collaborate and iterate together across an entire creative process. Learn more about the thinking behind this innovative research!

Inside Halide, the open source language engineers use to make imaging tools faster

Halide is an open-source embedded programming language co-developed by Adobe Research and MIT to make imaging tools faster and more portable across devices. We spoke with five key contributors to learn how it continues to evolve and enable tools used by billions, from digital cameras to many of Adobe’s products!