HistReNeRF：在当代神经辐射场重建中进行历史图像重定位

中文摘要 AI 辅助

在当代场景模型中对档案照片进行重定位极具挑战性，因为历史视图与现代视图在摄影外观、可见物体及空间布局上存在差异。为此，我们提出HistReNeRF，这一框架通过将适配后的DINOv2补丁特征与从当代神经辐射场（NeRF）重建中采样的候选射线进行匹配，来估计历史照片的6自由度（6-DoF）位姿。NeRF的连续表示提供了可查询的场景接口，可从中采样并匹配候选射线，从而直接在用于定位的特征表示中实现历史摄影与当代图像之间的域适配。我们在一个新的跨时间数据集上对基于嵌入空间的域适配与像素空间方法进行评估，该数据集包含来自三个欧洲地标的10545张当代街景图像和230张档案照片。在三个场景中，嵌入空间适配分别将平移误差和旋转误差平均降低了11%和16%。这些结果表明，神经场景重定位为特征空间适配提供了自然接口，无需修改查询图像即可减少跨时间外观偏移。代码和数据集可在this https URL获取。

英文摘要

Relocalising archival photographs within a contemporary scene model is challenging because historic and modern views can differ in photographic appearance, visible objects, and spatial layout. Therefore, we present HistReNeRF, a framework that estimates the 6-DoF pose of a historic photograph by matching adapted DINOv2 patch features to candidate rays sampled from a contemporary Neural Radiance Field (NeRF) reconstruction. The continuous representation of a NeRF provides a queryable scene interface from which candidate rays can be sampled and matched, enabling domain adaptation between historic photography and contemporary images directly in the feature representation used for localisation. We evaluate embedding-space-based domain adaptation against pixel-space methods on a new cross-temporal dataset comprising 10,545 contemporary street-level images and 230 archival photographs from three European landmarks. Embedding-space adaptation reduces translation and rotation errors by an average of 11% and 16%, respectively, across the three scenes. These results show that neural scene relocalisation provides a natural interface for feature-space adaptation, reducing cross-temporal appearance shift without modifying the query image. Code and dataset at https://github.com/ARTUROLab/HistReNeRF.

发表机构

• Durham University（杜伦大学）

机构由 AI 辅助整理，请以论文原文为准。