A new data pipeline using real photos, entity removal, and image-to-video models plus a cross-view attention loss enables text-driven generation of actors in reference scenes with improved alignment.
Places: A 10 million image database for scene recognition.IEEE Transactions on Pattern Analy- sis and Machine Intelligence, 2017
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
SketchDeco performs training-free sketch colourisation via diffusion inversion to insert user colors followed by custom self-attention blending for local fidelity and global harmony.
citing papers explorer
-
Setting the Stage: Text-Driven Scene-Consistent Image Generation
A new data pipeline using real photos, entity removal, and image-to-video models plus a cross-view attention loss enables text-driven generation of actors in reference scenes with improved alignment.
-
SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation
SketchDeco performs training-free sketch colourisation via diffusion inversion to insert user colors followed by custom self-attention blending for local fidelity and global harmony.