Neural graphics primitives, parameterized by fully connected neural networks, can be costly
to train and evaluate. We reduce this cost with a versatile new input encoding that permits …

Neural signed distance functions (SDFs) are emerging as an effective representation for 3D
shapes. State-of-the-art methods typically encode the SDF with a large, fixed-size neural …

Shape priors learned from data are commonly used to reconstruct 3D objects from partial or
noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D …

Neural approximations of scalar-and vector fields, such as signed distance functions and
radiance fields, have emerged as accurate, high-quality representations. State-of-the-art …

We present Dictionary Fields, a novel neural representation which decomposes a signal into
a product of factors, each represented by a classical or neural field representation, operating …

We present the first approach to volumetric performance capture and novel-view rendering
at real-time speed from monocular video, eliminating the need for expensive multi-view …

Inferring 3D locations and shapes of multiple objects from a single 2D image is a long-
standing objective of computer vision. Most of the existing works either predict one of these …

Neural graphics primitives are faster and achieve higher quality when their neural networks
are augmented by spatial data structures that hold trainable features arranged in a grid …

We introduce NeuralVDB, which improves on an existing industry standard for efficient
storage of sparse volumetric data, denoted VDB [Museth], by leveraging recent …

Parametric feature grid encodings have gained significant attention as an encoding
approach for neural fields since they allow for much smaller MLPs, which significantly …