Pith

open record

sign in

arxiv: 2412.02193 · v3 · pith:S3YU4SGR · submitted 2024-12-03 · cs.CV · cs.AI

LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:S3YU4SGRrecord.jsonopen to challenge →

classification cs.CV cs.AI
keywords layoutvlmvlmslayoutmodelsreasoningscenedemonstratedifferentiable
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

    cs.CV 2026-07 conditional novelty 6.0

    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.

  2. Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation

    cs.CV 2026-05 unverdicted novelty 6.0

    Introduces Layout-as-Policy (LaP) to turn 3D layout estimation into an iterative policy-learning refinement process for better physical coherence.

  3. STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System

    cs.CV 2026-05 unverdicted novelty 6.0

    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.

  4. ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python

    cs.CV 2026-04 unverdicted novelty 5.0

    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 composition...

  5. Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments

    cs.AI 2026-07 unverdicted novelty 3.0

    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.