Feeding scene-graph embeddings into a frozen LLM through a two-stage alignment and LoRA pipeline improves layout accuracy in relation-dense scenes, at the cost of small losses on simple two-object layouts.
In: Pro- ceedings of the IEEE/CVF International Conference on Computer Vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SG-Layout: Structured Scene Graph-Guided Layout Generation with LLMs
Feeding scene-graph embeddings into a frozen LLM through a two-stage alignment and LoRA pipeline improves layout accuracy in relation-dense scenes, at the cost of small losses on simple two-object layouts.