Presentation
IP-Composer: Semantic Composition of Visual Concepts
DescriptionIP-Composer is a novel, training-free method for compositional image generation from multiple reference images. Extending IP-Adapter, it uses natural language to identify concept-specific subspaces in CLIP, projects input images into these subspaces to extract targeted concepts, and fuses them into composite embeddings—enabling fine-grained, controllable generation across diverse visual concepts.
Event Type
Technical Paper
TimeWednesday, 13 August 20254:45pm - 4:55pm PDT
LocationWest Building, Rooms 118-120
ACM Digital Library
Journal Papers' PDFs
Conference Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Wednesday, 13 August 20253:45pm - 5:35pm PDTWest Building, Rooms 118-120
Livestreamed
Recorded
