Authors: Animesh Karnewar, Andrea Vedaldi, David Novotny, Niloy Mitra

project page: [ Ссылка ]
arxiv: [ Ссылка ]

Diffusion models have emerged as the best approach for generative modelling of 2D images. Part of their success is due to the possibility of training them on millions if not billions of images with a stable learning objective. However, extending these models to 3D remains difficult for two reasons. First, finding a large quantity of 3D training data is much harder than for 2D images. Second, while it is conceptually trivial to extend the models to operate on 3D rather than 2D grids, the associated cubic growth in memory and compute complexity makes this unfeasible. We address the first challenge by introducing a new diffusion setup that can be trained, end to-end, with only posed 2D images for supervision, and the second challenge by proposing an image formation model that decouples model memory from spatial memory. We evaluate our method on real-world data, using the CO3D dataset which has not been used to train 3D generative models before. We show that our diffusion models are scalable, train robustly, and are competitive in terms of sample quality and fidelity to existing approaches for 3D generative modelling.

свернуть