CVT (Centroidal Voronoi Tessellation)-based remeshing optimizes mesh quality via the Voronoi-Delaunay framework, optimizing vertex distribution and generating regular triangles. Current CVT-based approaches can fall into two categories. The former are exact methods, such as Geodesic CVT and Restricted Voronoi Diagrams(RVD), which ensure high quality but require significant computation. The latter are approximate methods, which reduce computational complexity yet compromise quality. To address this tradeoff, we propose a CVT-based surface remeshing method that balances optimization between quality and efficiency via curvature-adaptive multi-clipping of 3D Centroidal Voronoi cells using original surface facets. The core idea of the method is that we adaptively adjust the number of clipping times according to local curvature, and use the angular relationship between the normal vectors of neighboring facets to represent the magnitude of local curvature. Experimental results demonstrate the effectiveness of our method.

Object detection in aerial images based on deep learning requires a large amount of labeled data, whereas manual annotation of aerial images is time-consuming and laborious. As a branch of machine learning, active learning can help humans find the valuable samples by designing some corresponding query strategies, which effectively reduces the cost of manual labeling. However, objects in aerial images are usually small, dense, and accompanied by the interference from complex backgrounds. These brings considerable challenges for active learning in selecting high-value aerial image samples. Currently, there is a relatively lack of study on active learning for aerial images object detection. Therefore, this paper proposes an novel active learning method, using global-margin uncertainty (GMU) and collaborative sampling (CS) to find out the high valuable aerial image samples to reduce the annotation cost and improve the training efficiency of models. In GMU, the predicted scores of categories are applied to calculate the global uncertainty and margin uncertainty of unlabeled aerial images, then those aerial images with high uncertainty scores are selected as the candidate samples. In CS, we train a main model and an auxiliary model respectively to detect the candidate samples, where the samples with large differences in detection results of the two models are selected for manual annotation. The experiments conduct on VisDrone2019 and DOTA-v1.5 datasets, which showes that the proposed method has a better performance compared with several state-of-the-art active learning methods.

Abstract Triangular meshes of superior quality are important for geometric processing in practical applications. Existing approximative CVT‐based remeshing methodology uses planar polygonal facets to fit the original surface, simplifying the computational complexity. However, they usually do not consider surface curvature. Topological errors and outliers can also occur in the close sheet surface remeshing, resulting in wrong meshes. With this regard, we present a novel method named PowerRTF, an extension of the restricted tangent face (RTF) in conjunction with the power diagram, to better approximate the original surface with curvature adaption. The idea is to introduce a weight property to each sample point and compute the power diagram on the tangent face to produce area‐controlled polygonal facets. Based on this, we impose the variable‐capacity constraint and centroid constraint to the PowerRTF, providing the trade‐off between mesh quality and computational efficiency. Moreover, we apply a normal verification‐based inverse side point culling method to address the topological errors and outliers in close sheet surface remeshing. Our method independently computes and optimizes the PowerRTF per sample point, which is efficiently implemented in parallel on the GPU. Experimental results demonstrate the effectiveness, flexibility, and efficiency of our method.