WildCross Dataset
Abstract
WildCross is a cross-modal benchmark for place recognition and metric depth estimation in large-scale natural environments. WildCross comprises over 476K sequential RGB frames and 63K lidar submaps, each with accurate 6DoF ground truth poses, together with semi-dense depth and surface normal annotations for every image.
Fields of Study & Subjects
Robotics and Sensor-Based Localization
3D Surveying and Cultural Heritage
Advanced Vision and Imaging
Publication details
- Journal / source
- CSIRO
- Publication date
- 1 January 2026
- Language
- EN
- Document type
- Dataset