Non-autoregressive transformer with fine-grained optimization for user-specified indoor layout

Chao Song, Jie Wang, Shujie Chen, Haidong Li, Zhaoyi Jiang, Bailin Yang

Abstract: We present a novel framework that can generate plausible and diverse 3D (3 Dimensions) indoor scenes based on room floor plans and user-specified layout objects. In the framework, we construct a generative neural network with a non-autoregressive transformer to generate a reasonable distribution of layout objects, and then apply a fine-grained optimization process to adjust the sampled layout objects to optimal positions. Our non-autoregressive generative network addresses the issue of error chain accumulation, and the fine-grained optimization mitigates potential small collisions between layout objects. Furthermore, we trained the generative network using a publicly labeled 3D indoor dataset without additional manual processing, and provide detailed information on the capabilities of the generative network and the fine-grained optimization scheme. Extensive experiments demonstrate that our framework outperforms existing methods in learning the relationships between layout objects and layout rationality.