VRS-NeRF: Visual Relocalization with Sparse Neural Radiance Field

arXiv:2404.09271v1 Announce Type: new
Abstract: Visual relocalization is a key technique to autonomous driving, robotics, and virtual/augmented reality. After decades of explorations, absolute pose regression (APR), scene coordinate regression (SCR), and hierarchical methods (HMs) have become the most popular frameworks. However, in spite of high efficiency, APRs and SCRs have limited accuracy especially in large-scale outdoor scenes; HMs are accurate but need to store a large number of 2D descriptors for matching, resulting in poor efficiency. In this paper, we …

abstract accuracy arxiv augmented reality autonomous autonomous driving become cs.cv cs.ro driving efficiency frameworks hierarchical hms however key nerf neural radiance field popular reality regression robotics type virtual visual