3D-ARD+ unifies autoregressive token prediction with diffusion-based 3D latent generation to co-produce indoor scene layouts and object geometries that follow complex text-specified spatial and semantic constraints.
Illume: Illuminating your llms to see, draw, and self-enhance
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
other 1polarities
unclear 1representative citing papers
Function2Scene is a framework that parses functional design briefs into a 17-criteria taxonomy of constraints and applies iterative geometric-LLM-VLM refinement to produce 3D layouts preferred over LLM baselines in 94.3% of comparisons on 30 cases.
citing papers explorer
-
Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion
3D-ARD+ unifies autoregressive token prediction with diffusion-based 3D latent generation to co-produce indoor scene layouts and object geometries that follow complex text-specified spatial and semantic constraints.
-
Function2Scene: 3D Indoor Scene Layout from Functional Specifications
Function2Scene is a framework that parses functional design briefs into a 17-criteria taxonomy of constraints and applies iterative geometric-LLM-VLM refinement to produce 3D layouts preferred over LLM baselines in 94.3% of comparisons on 30 cases.