English

MARF: The Medial Atom Ray Field Object Representation

Graphics 2023-07-04 v1 Computer Vision and Pattern Recognition

Abstract

We propose Medial Atom Ray Fields (MARFs), a novel neural object representation that enables accurate differentiable surface rendering with a single network evaluation per camera ray. Existing neural ray fields struggle with multi-view consistency and representing surface discontinuities. MARFs address both using a medial shape representation, a dual representation of solid geometry that yields cheap geometrically grounded surface normals, in turn enabling computing analytical curvature despite the network having no second derivative. MARFs map a camera ray to multiple medial intersection candidates, subject to ray-sphere intersection testing. We illustrate how the learned medial shape quantities applies to sub-surface scattering, part segmentation, and aid representing a space of articulated shapes. Able to learn a space of shape priors, MARFs may prove useful for tasks like shape retrieval and shape completion, among others. Code and data can be found at https://github.com/pbsds/MARF.

Keywords

Cite

@article{arxiv.2307.00037,
  title  = {MARF: The Medial Atom Ray Field Object Representation},
  author = {Peder Bergebakken Sundt and Theoharis Theoharis},
  journal= {arXiv preprint arXiv:2307.00037},
  year   = {2023}
}

Comments

To be published in 3DOR 2023 and C&G Volume 114

R2 v1 2026-06-28T11:19:18.112Z