SynCity 3000 generates large, coherent 3D scenes from text by fine-tuning an image-to-3D diffusion model to operate convolutionally on overlapping windows, trained on procedurally generated synthetic scene data.
Layoutvlm: Differentiable optimization of 3d layout via vision-language models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demonstrate remarkable performance on some benchmarks, they still struggle with 3D reasoning tasks like arranging objects in space according to open-ended language instructions, particularly in dense and physically constrained environments. We introduce LayoutVLM, a framework and scene layout representation that exploits the semantic knowledge of Vision-Language Models (VLMs) and supports differentiable optimization to ensure physical plausibility. LayoutVLM employs VLMs to generate two mutually reinforcing representations from visually marked images, and a self-consistent decoding process to improve VLMs spatial planning. Our experiments show that LayoutVLM addresses the limitations of existing LLM and constraint-based approaches, producing physically plausible 3D layouts better aligned with the semantic intent of input language instructions. We also demonstrate that fine-tuning VLMs with the proposed scene layout representation extracted from existing scene datasets can improve their reasoning performance.
years
2026 5representative citing papers
Introduces Layout-as-Policy (LaP) to turn 3D layout estimation into an iterative policy-learning refinement process for better physical coherence.
STABLE generates simulation-ready tabletop scenes by alternating a semantic LLM reasoner for task-aligned coarse layouts with a physics corrector for physical plausibility using progressive scene expansion.
ProcFunc introduces a Python library with function-oriented abstractions for procedural 3D generation in Blender, enabling combinatorial scene creation and demonstrated via a new indoor room generator with compositional materials for synthetic data.
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
-
SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion
SynCity 3000 generates large, coherent 3D scenes from text by fine-tuning an image-to-3D diffusion model to operate convolutionally on overlapping windows, trained on procedurally generated synthetic scene data.
-
Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation
Introduces Layout-as-Policy (LaP) to turn 3D layout estimation into an iterative policy-learning refinement process for better physical coherence.
-
STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System
STABLE generates simulation-ready tabletop scenes by alternating a semantic LLM reasoner for task-aligned coarse layouts with a physics corrector for physical plausibility using progressive scene expansion.
-
ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python
ProcFunc introduces a Python library with function-oriented abstractions for procedural 3D generation in Blender, enabling combinatorial scene creation and demonstrated via a new indoor room generator with compositional materials for synthetic data.
-
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.