SceneBooth keeps a provided subject image untouched and paints a new background around it, guided by a caption, object labels, and a predicted scene layout.
Paint by example: Exemplar-based image editing with diffusion models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SceneBooth: Diffusion-based Framework for Subject-preserved Text-to-Image Generation
SceneBooth keeps a provided subject image untouched and paints a new background around it, guided by a caption, object labels, and a predicted scene layout.