ShowRoom3D: Text to High-Quality 3D Room Generation Using 3D Priors
This addresses the challenge for researchers and practitioners in 3D scene generation, offering an incremental improvement over prior methods that relied on 2D priors.
The paper tackled the problem of generating high-quality 3D room-scale scenes from text, achieving improved structural integrity, clarity, and consistency by using a 3D diffusion prior and a progressive optimization approach, with results significantly outperforming state-of-the-art methods in user studies.
We introduce ShowRoom3D, a three-stage approach for generating high-quality 3D room-scale scenes from texts. Previous methods using 2D diffusion priors to optimize neural radiance fields for generating room-scale scenes have shown unsatisfactory quality. This is primarily attributed to the limitations of 2D priors lacking 3D awareness and constraints in the training methodology. In this paper, we utilize a 3D diffusion prior, MVDiffusion, to optimize the 3D room-scale scene. Our contributions are in two aspects. Firstly, we propose a progressive view selection process to optimize NeRF. This involves dividing the training process into three stages, gradually expanding the camera sampling scope. Secondly, we propose the pose transformation method in the second stage. It will ensure MVDiffusion provide the accurate view guidance. As a result, ShowRoom3D enables the generation of rooms with improved structural integrity, enhanced clarity from any view, reduced content repetition, and higher consistency across different perspectives. Extensive experiments demonstrate that our method, significantly outperforms state-of-the-art approaches by a large margin in terms of user study.