Computer Vision News - December 2021

11 Muxingzi Li Alignment of multi-modal geometric data We present a global registration algorithm for multi-modal geometric data, typically 3D point clouds and meshes. Existing feature-based methods and recent deep learning based approaches typically rely upon point-to-point matching strategies that often fail to deliver accurate results from defect-laden data. In contrast, we reason at the scale of planar shapes whose detection from input data offers robustness on a range of defects, from noise to outliers through heterogeneous sampling. The detected planar shapes are projected into an accumulation space from which a rotational alignment is operated. A second step then refines the result with a local continuous optimization which also estimates the scale. We demonstrate the robustness and efficacy of our algorithmon challenging real-world data. In particular, we show that our algorithm competes well against state-of-the-art methods, especially on piece-wise planar objects and scenes. Polygonal image segmentation We present an algorithm for extracting and vectorizing objects in imageswith polygons. Departing from a polygonal partition that oversegments an image into convex cells, the algorithm refines the geometry of the partitionwhilelabelingitscellsbyasemantic class. The result is a set of polygons, each capturing an object in the image. The quality of a configuration is measured by an energy that accounts for both the fidelity to input data and the complexity of the output polygons. To efficiently explore the configuration space, we perform splitting and merging operations in tandem on the cells of the polygonal partition. The exploration mechanism is controlled by a priority queue that sorts the operations most likely todecrease theenergy.Weshow the potential of our algorithm on different types of scenes, from organic shapes to man-made objects through floor maps, and demonstrate its efficiency compared to existing vectorization methods.