Presentation
MAOAM: Unified Object and Material Selection with Vision-Language Models
SessionImage Editing
DescriptionMAOAM is a unified selection framework that enables precise object- and material- level selection across both text- and click-based interactions. MAOAM leverages a VLM which interprets the user's selection intent, and encodes information to the segmentation head. MAOAM achieves strong performance and generalization across varied objects, materials, and prompting scenarios.
Event Type
Technical Paper
TimeThursday, 23 July 202611:35am - 11:45am PDT
LocationRoom 408 B
Digital Library
PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Thursday, 23 July 202610:45am - 12:15pm PDTRoom 408 B
Full Conference Supporter
Full Conference
