FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Tongyuan, Bai, Wangyuanfan, Chen, Dong, Wu, Tieru, Li, Manyi, Ma, Rui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915321279938560
author Bai, Tongyuan
Bai, Wangyuanfan
Chen, Dong
Wu, Tieru
Li, Manyi
Ma, Rui
author_facet Bai, Tongyuan
Bai, Wangyuanfan
Chen, Dong
Wu, Tieru
Li, Manyi
Ma, Rui
contents Controllability plays a crucial role in the practical applications of 3D indoor scene synthesis. Existing works either allow rough language-based control, that is convenient but lacks fine-grained scene customization, or employ graph based control, which offers better controllability but demands considerable knowledge for the cumbersome graph design process. To address these challenges, we present FreeScene, a user-friendly framework that enables both convenient and effective control for indoor scene synthesis.Specifically, FreeScene supports free-form user inputs including text description and/or reference images, allowing users to express versatile design intentions. The user inputs are adequately analyzed and integrated into a graph representation by a VLM-based Graph Designer. We then propose MG-DiT, a Mixed Graph Diffusion Transformer, which performs graph-aware denoising to enhance scene generation. Our MG-DiT not only excels at preserving graph structure but also offers broad applicability to various tasks, including, but not limited to, text-to-scene, graph-to-scene, and rearrangement, all within a single model. Extensive experiments demonstrate that FreeScene provides an efficient and user-friendly solution that unifies text-based and graph based scene synthesis, outperforming state-of-the-art methods in terms of both generation quality and controllability in a range of applications.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02781
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts
Bai, Tongyuan
Bai, Wangyuanfan
Chen, Dong
Wu, Tieru
Li, Manyi
Ma, Rui
Computer Vision and Pattern Recognition
Controllability plays a crucial role in the practical applications of 3D indoor scene synthesis. Existing works either allow rough language-based control, that is convenient but lacks fine-grained scene customization, or employ graph based control, which offers better controllability but demands considerable knowledge for the cumbersome graph design process. To address these challenges, we present FreeScene, a user-friendly framework that enables both convenient and effective control for indoor scene synthesis.Specifically, FreeScene supports free-form user inputs including text description and/or reference images, allowing users to express versatile design intentions. The user inputs are adequately analyzed and integrated into a graph representation by a VLM-based Graph Designer. We then propose MG-DiT, a Mixed Graph Diffusion Transformer, which performs graph-aware denoising to enhance scene generation. Our MG-DiT not only excels at preserving graph structure but also offers broad applicability to various tasks, including, but not limited to, text-to-scene, graph-to-scene, and rearrangement, all within a single model. Extensive experiments demonstrate that FreeScene provides an efficient and user-friendly solution that unifies text-based and graph based scene synthesis, outperforming state-of-the-art methods in terms of both generation quality and controllability in a range of applications.
title FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.02781