WildCross: A Cross-Modal Large Scale Benchmark for Place Recognition and Metric Depth Estimation in Natural Environments
This provides a new benchmark for multi-modal robotic perception in unstructured natural settings, addressing a gap in existing datasets focused on urban environments.
The authors tackled the lack of datasets for robotic perception in natural environments by introducing WildCross, a cross-modal benchmark with over 476K RGB frames and annotations, which they validated through experiments on place recognition and depth estimation.
Recent years have seen a significant increase in demand for robotic solutions in unstructured natural environments, alongside growing interest in bridging 2D and 3D scene understanding. However, existing robotics datasets are predominantly captured in structured urban environments, making them inadequate for addressing the challenges posed by complex, unstructured natural settings. To address this gap, we propose WildCross, a cross-modal benchmark for place recognition and metric depth estimation in large-scale natural environments. WildCross comprises over 476K sequential RGB frames with semi-dense depth and surface normal annotations, each aligned with accurate 6DoF poses and synchronized dense lidar submaps. We conduct comprehensive experiments on visual, lidar, and cross-modal place recognition, as well as metric depth estimation, demonstrating the value of WildCross as a challenging benchmark for multi-modal robotic perception tasks. We provide access to the code repository and dataset at https://csiro-robotics.github.io/WildCross.