Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors
This addresses the challenge of open-set 3D object arrangement for generative AI, enabling personalized scene creation from predefined objects.
The paper tackles the problem of generating 3D scenes with multiple high-resolution objects by introducing Lay-A-Scene, which arranges unseen 3D objects using text-to-image priors, and it often generates coherent and feasible arrangements as evaluated with human raters.
Generating 3D visual scenes is at the forefront of visual generative AI, but current 3D generation techniques struggle with generating scenes with multiple high-resolution objects. Here we introduce Lay-A-Scene, which solves the task of Open-set 3D Object Arrangement, effectively arranging unseen objects. Given a set of 3D objects, the task is to find a plausible arrangement of these objects in a scene. We address this task by leveraging pre-trained text-to-image models. We personalize the model and explain how to generate images of a scene that contains multiple predefined objects without neglecting any of them. Then, we describe how to infer the 3D poses and arrangement of objects from a 2D generated image by finding a consistent projection of objects onto the 2D scene. We evaluate the quality of Lay-A-Scene using 3D objects from Objaverse and human raters and find that it often generates coherent and feasible 3D object arrangements.