Disentangled 3D Scene Generation with Layout Learning

We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained textto-image model. Our key insight is that objects can be discovered by finding parts of a 3D scene that, when rearranged spatially, still produce valid configurations of the same scene. Concretely, our method jointly optimizes multiple NeRFs from scratch-each representing its own object-along with a set of layouts that composite these objects into scenes. We then encourage these composited scenes to be in-distribution according to the image generator. We show that despite its simplicity, our approach successfully generates 3D scenes decomposed into individual objects, enabling new capabilities in text-to-3D content creation. See our project page for results and an interactive demo: https://dave.ml/layoutlearning/ While these models can generate high-quality samples, their internal workings are hard to interpret, and they do not explicitly represent the distinct 3D entities that make up the images they create. Nevertheless, the priors learned by these models have proven incredibly useful across various tasks involving 3D reasoning (