Geometric deep learning has sparked a rising interest in computer graphics to perform shape understanding tasks, such as shape classification and semantic segmentation. When the input is a polygonal surface, one has to suffer from the irregular mesh structure. Motivated by the geometric spectral theory, we introduce Laplacian2Mesh , a novel and flexible convolutional neural network (CNN) framework for coping with irregular triangle meshes (vertices may have any valence). By mapping the input mesh surface to the multi-dimensional Laplacian-Beltrami space, Laplacian2Mesh enables one to perform shape analysis tasks directly using the mature CNNs, without the need to deal with the irregular connectivity of the mesh structure. We further define a mesh pooling operation such that the receptive field of the network can be expanded while retaining the original vertex set as well as the connections between them. Besides, we introduce a channel-wise self-attention block to learn the individual importance of feature ingredients. Laplacian2Mesh not only decouples the geometry from the irregular connectivity of the mesh structure but also better captures the global features that are central to shape classification and segmentation. Extensive tests on various datasets demonstrate the effectiveness and efficiency of Laplacian2Mesh, particularly in terms of the capability of being vulnerable to noise to fulfill various learning tasks.

Surface reconstruction is a challenging task when input point clouds, especially real scans, are noisy and lack normals. Observing that the Multilayer Perceptron (MLP) and the implicit moving least-square function (IMLS) provide a dual representation of the underlying surface, we introduce Neural-IMLS , a novel approach that directly learns a noise-resistant signed distance function (SDF) from unoriented raw point clouds in a self-supervised manner. In particular, IMLS regularizes MLP by providing estimated SDFs near the surface and helps enhance its ability to represent geometric details and sharp features, while MLP regularizes IMLS by providing estimated normals. We prove that at convergence, our neural network produces a faithful SDF whose zero-level set approximates the underlying surface due to the mutual learning mechanism between the MLP and the IMLS. Extensive experiments on various benchmarks, including synthetic and real scans, show that Neural-IMLS can reconstruct faithful shapes even with noise and missing parts. The source code can be found at https://github.com/bearprin/Neural-IMLS .

The Kuwahara filter can generate local smoothed color regions similar to hand-painted strokes, and therefore it can be used to image artistic rendering. However, the existing Kuwahara filtering methods often adopt a fixed-sized filter kernel, which leads to homogeneous size of strokes. In view of this problem, a multi-scale anisotropic Kuwahara filtering method is proposed in this paper. By using image saliency as control information to adjust the size of filter kernel, strokes with abundant varied geometric scales are generated. This paper also presents an automatic rendering framework based on the proposed algorithm that automatically transforms images into an oil painting style. Using the image’s orientation field of edge, edge gradient magnitude and image saliency to control the bump mapping, the senses of thickness and layers of oil painting’s strokes are generated. By adopting this framework, an artistic oil painting style similar to the “impasto technique” can be simulated well.

Compressibility is a basic property of gelled crude oil, which was always regarded as a constant in the unsteady-pipe-flow process. In this article, the compressibility of gelled crude oil was accurately measured, and some new characteristics were discovered by a new apparatus that was developed using a special sealing method consisting of an elastic film and the Newtonian fluid. There was no leakage in the special hermetical method, and the unexpected seal-ring deformation of the piston in the traditional compression apparatus was also well-avoided. Using the new apparatus, compressibility of the gelled crude oil was tested and it was found that the compressibility of gelled crude oil is strongly time dependent.

To address the problem that the current optimization-based visual-inertial SLAM algorithms have difficulty in achieving high accuracy, high robustness and high efficiency at the same time, an efficient and versatile SLAM algorithm (EV-VINS) based on the improvement of VINS-Mono is proposed in this paper. EV-VINS tightly coupling the binocular and inertial measurement unit is divided into decoupled front-end, which detects GFTT corners and performs optical flow tracking, and back-end, which mainly performs initialization, nonlinear optimization and outlier rejection. The dense map module is added for subsequent navigation functions. In particular, a feature classification strategy is proposed based on the analysis of the existing problems in the initialization, which not only greatly reduces the number of outliers during initialization, but also makes the points used for back-end optimization have good initial values. Therefore, the computational efficiency and the stability of the back-end optimization are significantly improved while ensuring the accuracy. The simulation experiments based on the EuRoC datasets and actual test results show that EV-VINS has better real-time performance while having the basically same location accuracy compared to the classical algorithms.