<div align="center">
<h1>SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments</h1>
<div>
ECCV 2024
</div>
<div>
<a href='https://iphome.hhi.de/gard/index.htm' target='_blank'>Niklas Gard<sup>1,2</sup></a> 
<a href='https://iphome.hhi.de/hilsmann/index.htm' target='_blank'>Anna Hilsmann<sup>1</sup></a> 
<a href='https://iphome.hhi.de/eisert/index.htm' target='_blank'>Peter Eisert<sup>1,2</sup></a> 
</div>
<div>
Fraunhofer Heinrich Hertz Institute, HHI<sup>1</sup>, Humboldt University of Berlin<sup>2</sup>
</div>
</div>
**SPVLoc** estimates the **indoor 6D camera pose** by determining the image position and orientation relative to a **minimalistic, semantically annotated 3D model**.
This model is represented by a set of synthetic panoramic images, from which the method identifies the optimal panoramic match using semantic viewport matching.
Finally, the 6D pose is estimated relative to the location of the …
