Learning to Follow Object-Centric Image Editing Instructions Faithfully

Natural language instructions are a powerful interface for editing the outputs of text-to-image diffusion models. However, several challenges need to be addressed: 1) underspecification (the need to model the implicit meaning of instructions) 2) grounding (the need to localize where the edit has to...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Chakrabarty, Tuhin, Singh, Kanishk, Saakyan, Arkadiy, Muresan, Smaranda
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!