NeRF-Supervised Feature Point Detection and Description

arXiv:2403.08156v1 Announce Type: new
Abstract: 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 introduces a novel approach leveraging neural radiance fields (NeRFs) for realistic multi-view training data generation. We create a diverse multi-view dataset using NeRFs, consisting of indoor and outdoor scenes. …

abstract applications arxiv computer computer vision cs.cv detection feature homography nerf novel paper perspectives recognition simulations slam training type view vision visual visual slam