We present Manifold Diffusion Fields (MDF), an approach to learn generat...
Diffusion probabilistic models have quickly become a major approach for
...
We study the problem of novel view synthesis of a scene comprised of 3D
...
Deep linear networks trained with gradient descent yield low rank soluti...
We analyze the learning dynamics of infinitely wide neural networks with...
We tackle the challenge of learning a distribution over complex, realist...
State-of-the-art learning-based monocular 3D reconstruction methods lear...
We examine Generative Adversarial Networks (GANs) through the lens of de...
Deep neural networks require collecting and annotating large amounts of ...