Abstract
In this paper, we present Neural Adaptive Tomography (NeAT), the first adaptive, hierarchical neural rendering pipeline for tomography. Through a combination of neural features with an adaptive explicit representation, we achieve reconstruction times far superior to existing neural inverse rendering methods. The adaptive explicit representation improves efficiency by facilitating empty space culling and concentrating samples in complex regions, while the neural features act as a neural regularizer for the 3D reconstruction. The NeAT framework is designed specifically for the tomographic setting, which consists only of semi-transparent volumetric scenes instead of opaque objects. In this setting, NeAT outperforms the quality of existing optimization-based tomography solvers while being substantially faster.
Original language | English (US) |
---|---|
Article number | 55 |
Journal | ACM transactions on graphics |
Volume | 41 |
Issue number | 4 |
DOIs | |
State | Published - Jul 22 2022 |
Bibliographical note
Publisher Copyright:© 2022 Association for Computing Machinery.
Keywords
- Implicit neural representation
- Octree
- X-ray computed tomography
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design