NeRF监督的特征点检测与描述
NeRF-Supervised Feature Point Detection and Description
AI总结：
本文提出利用NeRF生成多样真实数据集，通过透视投影几何监督训练特征点检测与描述模型，在相对位姿估计等任务上以更少数据和时间取得竞争或更优性能。
摘要：
特征点检测与描述是多种计算机视觉应用（如运动恢复结构、视觉SLAM和视觉位置识别）的核心。尽管基于学习的方法已超越传统手工技术，但其训练通常依赖基于单应性的多视角模拟，限制了模型的泛化能力。本文提出一种新方法，利用神经辐射场生成包含室内外场景的多样且真实的数据集。所提方法使最先进的特征检测器和描述符适应多视角NeRF合成数据的训练，并通过透视投影几何实现监督。实验表明，该方法在相对位姿估计、点云配准和单应性估计的标准基准上取得竞争或更优的性能，且与现有方法相比，所需训练数据和时间显著减少。
英文摘要：
Feature point detection and description is the backbone for various computer vision applications, such as Structure-from-Motion, visual SLAM, and visual place recognition. While learning-based methods have surpassed traditional handcrafted techniques, their training often relies on simplistic homography-based simulations of multi-view perspectives, limiting model generalisability. This paper presents a novel approach leveraging Neural Radiance Fields (NeRFs) to generate a diverse and realistic dataset consisting of indoor and outdoor scenes. Our proposed methodology adapts state-of-the-art feature detectors and descriptors for training on multi-view NeRF-synthesised data, with supervision achieved through perspective projective geometry. Experiments demonstrate that the proposed methodology achieves competitive or superior performance on standard benchmarks for relative pose estimation, point cloud registration, and homography estimation while requiring significantly less training data and time compared to existing approaches.
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。
