中文

RePose-NeRF:针对噪声相机姿态的鲁棒辐射场

计算机视觉与模式识别 2025-11-12 v1

摘要

从多视图图像进行精确3D重建对于下游机器人任务(如导航、操控和环境理解)至关重要。然而,在实际场景中获取精确的相机姿态仍然具有挑战性,即使已知标定参数亦然。这限制了现有NeRF方法的实用性,这些方法高度依赖准确的外参估计。此外,这些方法的隐式体积表示与广泛采用的多边形网格存在显著差异,使得在标准3D软件中进行渲染和操作效率低下。本文提出了一种鲁棒框架,从多视图图像中利用含噪声外参参数直接重建高质量、可编辑的3D网格。我们的方法在 jointly 优化相机姿态的同时学习一个能捕捉细节几何和逼真外观的隐式场景表示。生成的网格与常见的3D图形和机器人工具兼容,支持后续高效使用。实验在标准基准数据集上表明,我们的方法在姿态不确定性下实现了精确且鲁棒的3D重建,弥合了神经隐式表示与实际机器人应用之间的鸿沟。

关键词

引用

@article{arxiv.2511.08545,
  title  = {RePose-NeRF: Robust Radiance Fields for Mesh Reconstruction under Noisy Camera Poses},
  author = {Sriram Srinivasan and Gautam Ramachandra},
  journal= {arXiv preprint arXiv:2511.08545},
  year   = {2025}
}

备注

Several figures are included to illustrate the reconstruction and rendering quality of the proposed method, which is why the submission exceeds the 50MB file size limit. > Several figures are included to illustrate the reconstruction and rendering quality of the proposed method, which is why the submission exceeds the 50,000 KB file size limit (Now this has been resolved)