RePose-NeRF：嘈杂相机位姿下用于网格重建的鲁棒辐射场
RePose-NeRF: Robust Radiance Fields for Mesh Reconstruction under Noisy Camera Poses
AI总结：
针对现实场景中相机位姿嘈杂导致现有NeRF方法实用性受限的问题，提出RePose-NeRF鲁棒框架，联合优化位姿与隐式场景表示，直接重建高质量可编辑3D网格，在标准基准上实现准确鲁棒重建，弥合神经隐式表示与机器人应用的差距。
摘要：
从多视图图像中准确重建3D模型对于导航、操纵和环境理解等下游机器人任务至关重要。然而，即使已知校准参数，在现实场景中获取精确的相机位姿仍然具有挑战性。这限制了现有严重依赖精确外参估计的基于NeRF的方法的实用性。此外，它们的隐式体积表示与广泛采用的多边形网格存在显著差异，导致在标准3D软件中渲染和操纵效率低下。在这项工作中，我们提出了一个鲁棒框架，可直接从具有嘈杂外参的多视图图像中重建高质量、可编辑的3D网格。我们的方法在学习捕获精细几何细节和逼真外观的隐式场景表示的同时，联合优化相机位姿。生成的网格与常见的3D图形和机器人工具兼容，可实现高效的下游使用。在标准基准上的实验表明，我们的方法在存在位姿不确定性的情况下实现了准确且鲁棒的3D重建，弥合了神经隐式表示与实际机器人应用之间的差距。
英文摘要：
Accurate 3D reconstruction from multi-view images is essential for downstream robotic tasks such as navigation, manipulation, and environment understanding. However, obtaining precise camera poses in real-world settings remains challenging, even when calibration parameters are known. This limits the practicality of existing NeRF-based methods that rely heavily on accurate extrinsic estimates. Furthermore, their implicit volumetric representations differ significantly from the widely adopted polygonal meshes, making rendering and manipulation inefficient in standard 3D software. In this work, we propose a robust framework that reconstructs high-quality, editable 3D meshes directly from multi-view images with noisy extrinsic parameters. Our approach jointly refines camera poses while learning an implicit scene representation that captures fine geometric detail and photorealistic appearance. The resulting meshes are compatible with common 3D graphics and robotics tools, enabling efficient downstream use. Experiments on standard benchmarks demonstrate that our method achieves accurate and robust 3D reconstruction under pose uncertainty, bridging the gap between neural implicit representations and practical robotic applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
