CHOrD: Generation of Collision-Free, House-Scale, and Organized Digital Twins for 3D Indoor Scenes with Controllable Floor Plans and Optimal Layouts
This addresses the need for scalable, high-quality 3D indoor scene generation for applications like virtual reality and simulation, though it appears incremental by building on existing methods with new controls and representations.
The authors tackled the problem of generating 3D indoor scenes by introducing CHOrD, a framework that creates house-scale, collision-free digital twins with controllable floor plans, achieving state-of-the-art performance on 3D-FRONT and their proposed dataset.
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.