LoD-Loc tackles visual localization w.r.t a scene represented as LoD 3D map. Given a query image and its pose prior, the method utilizes the wireframe of LoD models to recover the camera pose. This ...

Abstract: Scene text segmentation is to predict pixel-wise text regions from an image, enabling in-image text editing or removal. One of the primary challenges is to remove noises including non-text ...

Abstract: As the demand for large-scale geographic spatial information applications grows, traditional raster tile maps have become inadequate in meeting users' needs for high-resolution rendering and ...