SynergyAmodal co-synthesizes a 16K amodal dataset from EntitySeg images with human and model guidance, and trains a diffusion model that completes occluded objects with optional text control.
Kosiorek, Oiwi Parker Jones, and Ingmar Posner
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SynergyAmodal: Deocclude Anything with Text Control
SynergyAmodal co-synthesizes a 16K amodal dataset from EntitySeg images with human and model guidance, and trains a diffusion model that completes occluded objects with optional text control.