PolyCubes provide compact representations for closed complex shapes and are essential to many computer graphics applications. Existing automatic PolyCube construction methods usually suffer from poor quality or time-consuming computation. In this paper, we provide a highly efficient method to compute volumetric PolyCube-maps. Given an input tetrahedral mesh, we utilize two novel normal-driven volumetric deformation schemes and a polycube-allowable mesh segmentation to drive the input to a volumetric PolyCube structure. Our method can robustly generate foldover-free and low-distortion PolyCube-maps in practice, and provide a flexible control on the number of corners of Polycubes. Compared with state-of-the-art methods, our method is at least one order of magnitude faster and has better mapping qualities. We demonstrate the efficiency and efficacy of our method in PolyCube construction and all-hexahedral meshing on various complex models. (a) Armadillo (σ =le) 236 corners J min = 0.265 Javg = 0.909 (b) Armadillo (σ = 1.5le) 150 corners J min = 0.185 Javg = 0.901 (c) Bimba (σ =le) 68 corners J min = 0.361 Javg = 0.935 (d) Bimba (σ = 2.0le) 34 corners J min = 0.276 Javg = 0.910 (e) Sphinx (σ =le) 72 corners J min = 0.385 Javg = 0.948 (f) Sphinx (σ = 2.0le) 16 corners J min = 0.300 Javg = 0.930 X. Fu & C. Bai & Y. Liu / Efficient Volumetric PolyCube-Map Construction (a) [GSZ11] J min = 0.138 Javg = 0.930 (b) [LVS * 13] J min = 0.274 Javg = 0.938 (c) [HJS * 14] J min = 0.382 Javg = 0.926 (d) Ours J min = 0.422 Javg = 0.942 (e) [GSZ11] J min = 0.235 Javg = 0.925 (f) [LVS * 13] J min = 0.401 Javg = 0.926 (g) [HJS * 14] J min = 0.302 Javg = 0.934 (h) Ours J min = 0.439 Javg = 0.943
To improve the accessibility of smart devices and to simplify their usage, building models which understand user interfaces (UIs) and assist users to complete their tasks is critical. However, unique challenges are proposed by UI-specific characteristics, such as how to effectively leverage multimodal UI features that involve image, text, and structural metadata and how to achieve good performance when high-quality labeled data is unavailable. To address such challenges we introduce UIBert, a transformer-based joint image-text model trained through novel pre-training tasks on large-scale unlabeled UI data to learn generic feature representations for a UI and its components. Our key intuition is that the heterogeneous features in a UI are self-aligned, i.e., the image and text features of UI components, are predictive of each other. We propose five pretraining tasks utilizing this self-alignment among different features of a UI component and across various components in the same UI. We evaluate our method on nine real-world downstream UI tasks where UIBert outperforms strong multimodal baselines by up to 9.26% accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.