English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Camera localization aims to estimate 6 DoF camera poses from RGB images.Traditional methods detect and match interest points between a query image anda pre-built 3D model. Recent learning-based approaches encode scene structuresinto a specific convolutional neural network (CNN) and thus are able to predictdense coordinates from RGB images. However, most of them require re-training orre-adaption for a new scene and have difficulties in handling large-scalescenes due to limited network capacity. We present a new method for sceneagnostic camera localization using dense scene matching (DSM), where a costvolume is constructed between a query image and a scene. The cost volume andthe corresponding coordinates are processed by a CNN to predict densecoordinates. Camera poses can then be solved by PnP algorithms. In addition,our method can be extended to temporal domain, which leads to extra performanceboost during testing time. Our scene-agnostic approach achieves comparableaccuracy as the existing scene-specific approaches, such as KFNet, on the7scenes and Cambridge benchmark. This approach also remarkably outperformsstate-of-the-art scene-agnostic dense coordinate regression network SANet. TheCode is available at https://github.com/Tangshitao/Dense-Scene-Matching.

Learning Camera Localization via Dense Scene Matching