Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM

TL;DR

Chat2Layout introduces an interactive system leveraging multimodal large language models for dynamic 3D furniture layout design, enabling user-guided, feedback-driven interior arrangement without model retraining.

Contribution

The paper presents a novel interactive furniture layout system using MLLMs with a unified vision-question paradigm and a training-free visual prompting mechanism.

Findings

Enables language-interactive 3D furniture arrangement.

Supports bidirectional communication with MLLMs for layout refinement.

Demonstrates effectiveness on complex interior design tasks.

Abstract

Automatic furniture layout is long desired for convenient interior design. Leveraging the remarkable visual reasoning capabilities of multimodal large language models (MLLMs), recent methods address layout generation in a static manner, lacking the feedback-driven refinement essential for interactive user engagement. We introduce Chat2Layout, a novel interactive furniture layout generation system that extends the functionality of MLLMs into the realm of interactive layout design. To achieve this, we establish a unified vision-question paradigm for in-context learning, enabling seamless communication with MLLMs to steer their behavior without altering model weights. Within this framework, we present a novel training-free visual prompting mechanism. This involves a visual-text prompting technique that assist MLLMs in reasoning about plausible layout plans, followed by an Offline-to-Online search (O2O-Search) method, which automatically identifies the minimal set of informative references to provide exemplars for visual-text prompting. By employing an agent system with MLLMs as the core controller, we enable bidirectional interaction. The agent not only comprehends the 3D environment and user requirements through linguistic and visual perception but also plans tasks and reasons about actions to generate and arrange furniture within the virtual space. Furthermore, the agent iteratively updates based on visual feedback from execution results. Experimental results demonstrate that our approach facilitates language-interactive generation and arrangement for diverse and complex 3D furniture.