CHOrD：生成無碰撞、住宅規模且結構化的3D室內場景數位孿生，具可控平面圖與最佳佈局

CHOrD: Generation of Collision-Free, House-Scale, and Organized Digital Twins for 3D Indoor Scenes with Controllable Floor Plans and Optimal Layouts

March 15, 2025

作者: Chong Su, Yingbin Fu, Zheyuan Hu, Jing Yang, Param Hanji, Shaojun Wang, Xuan Zhao, Cengiz Öztireli, Fangcheng Zhong

cs.AI

摘要

我們介紹了CHOrD，這是一個用於可擴展合成3D室內場景的新框架，旨在創建房屋規模、無碰撞且具有層次結構的室內數字孿生。與現有方法直接將場景佈局合成為場景圖或物體列表不同，CHOrD引入了一種基於2D圖像的中間佈局表示，通過在生成過程中成功捕捉這些異常分佈（OOD）場景，有效防止了碰撞偽影的產生。此外，與現有方法不同，CHOrD能夠生成符合複雜平面圖的多模態控制場景佈局，從而創建出在房間結構的幾何和語義變化下均保持一致的房屋範圍佈局。我們還提出了一個新數據集，該數據集擴展了家居物品和房間配置的覆蓋範圍，並顯著提高了數據質量。CHOrD在3D-FRONT和我們提出的數據集上均展示了最先進的性能，提供了可適應任意平面圖變化的逼真且空間連貫的室內場景合成。

English

We introduce CHOrD, a novel framework for scalable synthesis of 3D indoor scenes, designed to create house-scale, collision-free, and hierarchically structured indoor digital twins. In contrast to existing methods that directly synthesize the scene layout as a scene graph or object list, CHOrD incorporates a 2D image-based intermediate layout representation, enabling effective prevention of collision artifacts by successfully capturing them as out-of-distribution (OOD) scenarios during generation. Furthermore, unlike existing methods, CHOrD is capable of generating scene layouts that adhere to complex floor plans with multi-modal controls, enabling the creation of coherent, house-wide layouts robust to both geometric and semantic variations in room structures. Additionally, we propose a novel dataset with expanded coverage of household items and room configurations, as well as significantly improved data quality. CHOrD demonstrates state-of-the-art performance on both the 3D-FRONT and our proposed datasets, delivering photorealistic, spatially coherent indoor scene synthesis adaptable to arbitrary floor plan variations.