# OX-NeRF: 3D X-ray Tomography Reconstruction from Sparse Views Using Implicit Neural Representation

arXiv: https://arxiv.org/abs/2610.11547 · HTML: https://mlsanity.com/paper/2610.11547/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Endoscopic and medical 3D reconstruction, one of 15 directions in 3D reconstruction and neural rendering.
- Builds on 0 of its 54 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- 3D reconstruction and neural rendering / [Endoscopic and medical 3D reconstruction](https://mlsanity.com/recon3d/endoscopic-and-medical-3d-reconstruction/)

## Abstract (arXiv)

NeRF and Gaussian splatting methods have been successfully applied on X-ray scenes where the views are too sparse for 3D reconstruction via classical methods. Ultra-sparse scenes with 10 or fewer views such as those with high-rate or low-dose acquisition still, however, present a significant challenge. To address this problem we present a new framework, Optimised X-ray Neural Radiance Fields (OX-NeRF), that combines cross-scene feature learning with scene-specific optimisation to reconstruct sets of related scenes. OX-NeRF employs a convolutional neural network (CNN) to identify cross-scene features while maintaining scene-specific multi-resolution hash grids of spatial features. The paired representations are fused and passed to a multilayer perceptron (MLP); the CNN, hash grids and MLP are then jointly optimised end-to-end. Benchmarking on parallel-beam and cone-beam X-ray datasets shows OX-NeRF provides significantly higher reconstruction accuracy on ultra-sparse scenes compared to existing radiance field methods.