Bird’s-Eye-View (BEV) maps have emerged as one of the most powerful representations for scene understanding due to their ability provide rich spatial context while being easy interpret and process. Such found use in many real-world tasks that extensively rely on accurate segmentation well object instance identification BEV space operation. However, existing algorithms only predict semantics spa...

Wide-area 3D data generation for complex urban environments often needs to leverage a mixed use of collected from both air and ground platforms, such as aerial surveys, satellite, mobile vehicles. On one hand, kind with information drastically different views (ca. 90° more) forming cross-view data, which due very limited overlapping region caused by the line sight sensors, is difficult be regis...

Image-based localization has been widely used for autonomous vehicles, robotics, augmented reality, etc., and this is carried out by matching a query image taken from cell phone or vehicle dashcam to large scale of geo-tagged reference images, such as satellite/aerial images Google Street Views. However, the problem remains challenging due inconsistency between large-scale datasets regarding va...