发表机构
University of Oxford（牛津大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对10个及以下视图的超稀疏X射线场景3D重建难题，提出OX-NeRF框架，结合跨场景特征学习与场景特定优化，经基准测试其重建精度显著优于现有辐射场方法。
AI 中文摘要
NeRF和高斯溅射方法已成功应用于X射线场景，这类场景的视图过于稀疏，无法通过经典方法进行3D重建。然而，视图数量为10个或更少的超稀疏场景，例如那些采用高剂量或低剂量采集的场景，仍然是一个重大挑战。为解决该问题，我们提出了一种新框架——优化型X射线神经辐射场（Optimised X-ray Neural Radiance Fields，OX-NeRF），该框架结合跨场景特征学习与场景特定优化，以重建一组相关场景。OX-NeRF采用卷积神经网络（CNN）识别跨场景特征，同时保留空间特征的场景特定多分辨率哈希网格，配对的表示被融合并传递至多层感知器（MLP）；随后对CNN、哈希网格和MLP进行端到端联合优化。在平行束和锥束X射线数据集上的基准测试表明，与现有辐射场方法相比，OX-NeRF在超稀疏场景上提供了显著更高的重建精度。
英文摘要
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.
