SpatialGrammar provides a grid-based DSL and compiler that lets LLMs generate collision-free 3D indoor scenes more reliably than raw-coordinate or code-based approaches.
Kenny Jones, Qiuhong Anna Wei, Kailiang Fu, and Daniel Ritchie
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
SDesc3D produces more plausible 3D indoor scenes from short texts by augmenting inputs with multi-view structural priors, functionality-aware grounding, and iterative self-rectification.
VIGA introduces a training-free interleaved multimodal reasoning loop that improves vision-as-inverse-graphics accuracy over one-shot baselines on BlenderGym, SlideBench, and new BlenderBench.
A generative model writes programs in a relational constraint DSL and uses bootstrapping to learn object placement distributions that align more closely with human annotations than data-driven or LLM baselines.
Pair2Scene generates complex 3D scenes beyond training data by training a network on local object-pair placement rules and applying them recursively with collision-aware sampling.
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
SPG-Layout combines statistical object priors with hierarchical large-object-first placement to produce physically plausible text-driven 3D scenes in non-Manhattan rooms and outperforms baselines on a new 500-scene benchmark.
citing papers explorer
-
SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation
SpatialGrammar provides a grid-based DSL and compiler that lets LLMs generate collision-free 3D indoor scenes more reliably than raw-coordinate or code-based approaches.
-
SDesc3D: Towards Layout-Aware 3D Indoor Scene Generation from Short Descriptions
SDesc3D produces more plausible 3D indoor scenes from short texts by augmenting inputs with multi-view structural priors, functionality-aware grounding, and iterative self-rectification.
-
Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
VIGA introduces a training-free interleaved multimodal reasoning loop that improves vision-as-inverse-graphics accuracy over one-shot baselines on BlenderGym, SlideBench, and new BlenderBench.
-
Learning to Place Objects with Programs and Iterative Self Training
A generative model writes programs in a relational constraint DSL and uses bootstrapping to learn object placement distributions that align more closely with human annotations than data-driven or LLM baselines.
-
Pair2Scene: Learning Local Object Relations for Procedural Scene Generation
Pair2Scene generates complex 3D scenes beyond training data by training a network on local object-pair placement rules and applying them recursively with collision-aware sampling.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
-
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
SPG-Layout combines statistical object priors with hierarchical large-object-first placement to produce physically plausible text-driven 3D scenes in non-Manhattan rooms and outperforms baselines on a new 500-scene benchmark.