MMGDreamer generates 3D indoor scenes from a mixed-modality scene graph whose nodes can be text, images, or both, and it predicts missing object relationships for more coherent layouts.
Title resolution pending
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
-
MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation
MMGDreamer generates 3D indoor scenes from a mixed-modality scene graph whose nodes can be text, images, or both, and it predicts missing object relationships for more coherent layouts.