Kevin Blackburn-Matzen

Kevin is a research scientist at Adobe Research. Their research focus is how to use Internet-scale data to aide the understanding of the visual world. Prior to joining Adobe, Kevin was a research scientist at Facebook working on AR/VR. Kevin received their PhD from Cornell University in 2016 under the supervision of Noah Snavely and Kavita Bala.

See more at kmatzen.com.

AI & Machine Learning Computer Vision, Imaging & Video Graphics (2D & 3D)

Publications

June 30, 2026 CVPR 2026

3D Space as a Scratchpad for Editable Text-to-Image Generation

Oindrila Saha, Vojtěch Krs, Radomír Měch, Subhransu Maji, Matheus Gadelha, Kevin Blackburn-Matzen

Computer Vision, Imaging & Video Graphics (2D & 3D)

News

SIGMA-GEN: Placing any subject, anywhere, exactly where you want it

SIGMA-GEN is an experimental unified framework from Adobe Research, presented at ICLR 2026, for multi-identity-preserving image generation — placing multiple subjects into a scene in a single pass, with each subject's appearance faithfully preserved.

April 1, 2026