DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis
This addresses the challenge of automated 3D scene generation for applications like virtual reality and interior design, representing a novel method for a known bottleneck in scene synthesis.
The paper tackles the problem of generating realistic and diverse indoor 3D scenes by introducing DiffuScene, a denoising diffusion model that synthesizes unordered object sets with attributes like location and semantics, resulting in more physically plausible scenes than state-of-the-art methods on the 3D-FRONT dataset.
We present DiffuScene for indoor 3D scene synthesis based on a novel scene configuration denoising diffusion model. It generates 3D instance properties stored in an unordered object set and retrieves the most similar geometry for each object configuration, which is characterized as a concatenation of different attributes, including location, size, orientation, semantics, and geometry features. We introduce a diffusion network to synthesize a collection of 3D indoor objects by denoising a set of unordered object attributes. Unordered parametrization simplifies and eases the joint distribution approximation. The shape feature diffusion facilitates natural object placements, including symmetries. Our method enables many downstream applications, including scene completion, scene arrangement, and text-conditioned scene synthesis. Experiments on the 3D-FRONT dataset show that our method can synthesize more physically plausible and diverse indoor scenes than state-of-the-art methods. Extensive ablation studies verify the effectiveness of our design choice in scene diffusion models.