No abstract

The advancement of deep learning technology has been concentrating on deploying end-to-end solutions using high dimensional data, such as images. Recently, a number of methods have been proposed for reconstructing 3D objects using deep learning. One such technique is the method that involves recovering 3D objects as voxel grids using one or multiple images. However, there has been very little work directed towards the generation of 3D objects represented by a set of points, i.e. point cloud, from voxel grids which are ambiguous and coarse. The development of a deep learning model that generates point clouds with details from coarse voxel grids has numerous benefits to quality of life. For example, design professionals can use this model to generate detailed 3D point clouds using a sketched and coarse voxel to enable their creativities. This paper presents an algorithm to generate point clouds from voxel grids. The algorithm explicitly loads 3D objects into voxels without projection operations and associated information loss. To obtain a comprehensive understanding of the voxel grid, the grid is analyzed through various angles, as inspired by how humans observe 3D objects. The features from various angles are passed into a GRU layer to extract patterns across views, which will then be passed to a channel-wise convolutional layer and graph convolution to generated the predicted point cloud. The experimental result of the algorithm indicates that the algorithm is capable of generating high-quality point clouds by understanding the semantic features of the voxel grid. INDEX TERMS 3D object generation, neural networks, point clouds.

No abstract

No abstract

Despite the development of therapeutic strategies, cancer is the second death cause worldwide and still rising. Unclear molecular mechanisms of carcinogenesis and lack of biomarkers for early diagnosis or advanced management are responsible for the poor prognosis of cancer. Recently, exosomes have been the focus of tumor studies, as they carry many biomolecules including proteins, lipids, and nucleic acids, and transfer them to participate in tumor development. Among the biomolecules, noncoding RNAs including microRNAs (miRNAs), long noncoding RNAs (lncRNAs), and circular RNAs (circRNAs) in exosomes have been found to participate in carcinogenesis and gain more attention. Compared with lncRNAs and miRNAs, the exosomal circRNAs are less studied in tumor studies. However, circRNAs are enriched and more stable in exosomes because of their covalently closed‐loop structures, protection provided by exosomes, and protein binding partners. Furthermore, exosomal circRNAs display more potent sponge effect for miRNAs, as they contain more miRNA response elements than lncRNAs. In this review, we highlighted the functional roles of exosomal circRNAs on the tumor progression including tumor growth, invasion, metabolism, immunomodulation, and chemotherapeutic drug resistance. Moreover, we also summarized predictive potency and clinical use of exosomal circRNAs in cancer.