Programmable-Room: Interactive Textured 3D Room Meshes Generation Empowered by Large Language Models

TL;DR

Programmable-Room is a framework that uses large language models and visual programming to interactively generate and edit textured 3D room meshes from natural language instructions, enabling precise and flexible room design.

Contribution

It introduces a unified framework combining LLMs and visual programming for detailed 3D room mesh generation and editing from natural language, with novel modules including a diffusion-based panorama generator.

Findings

Demonstrates flexible and precise 3D room editing capabilities

Outperforms existing models in quality and usability

Utilizes a diffusion model with optimized training for panorama generation

Abstract

We present Programmable-Room, a framework which interactively generates and edits a 3D room mesh, given natural language instructions. For precise control of a room's each attribute, we decompose the challenging task into simpler steps such as creating plausible 3D coordinates for room meshes, generating panorama images for the texture, constructing 3D meshes by integrating the coordinates and panorama texture images, and arranging furniture. To support the various decomposed tasks with a unified framework, we incorporate visual programming (VP). VP is a method that utilizes a large language model (LLM) to write a Python-like program which is an ordered list of necessary modules for the various tasks given in natural language. We develop most of the modules. Especially, for the texture generating module, we utilize a pretrained large-scale diffusion model to generate panorama images conditioned on text and visual prompts (i.e., layout, depth, and semantic map) simultaneously. Specifically, we enhance the panorama image generation quality by optimizing the training objective with a 1D representation of a panorama scene obtained from bidirectional LSTM. We demonstrate Programmable-Room's flexibility in generating and editing 3D room meshes, and prove our framework's superiority to an existing model quantitatively and qualitatively. Project page is available in https://jihyun0510.github.io/Programmable_Room_Page/.