Search

3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point cloud convolutions can be invariant to translation and point permutation, investigations of the rotation invariance property for point cloud convolution has been so far scarce. Some existing methods perform point cloud convolutions with rotation-invariant features, existing methods generally do not perform as well as translation-invariant only counterpart. In this work, we argue that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive. To address this problem, we propose a simple yet effective convolution operator that enhances feature distinction by designing powerful rotation invariant features from the local regions. We consider the relationship between the point of interest and its neighbors as well as the internal relationship of the neighbors to largely improve the feature descriptiveness. Our network architecture can capture both local and global context by simply tuning the neighborhood size in each convolution layer. We conduct several experiments on synthetic and real-world point cloud classifications, part segmentation, and shape retrieval to evaluate our method, which achieves the state-of-the-art accuracy under challenging rotations. [ABSTRACT FROM AUTHOR]

Feature matching aims at generating correspondences across images, which is widely used in many computer vision tasks. Although considerable progress has been made on feature descriptors and fast matching for initial correspondence hypotheses, selecting good ones from them is still challenging and critical to the overall performance. More importantly, existing methods often take a long computational time, limiting their use in real-time applications. This paper attempts to separate true correspondences from false ones at high speed. We term the proposed method (GMS) grid-based motion Statistics, which incorporates the smoothness constraint into a statistic framework for separation and uses a grid-based implementation for fast calculation. GMS is robust to various challenging image changes, involving in viewpoint, scale, and rotation. It is also fast, e.g., take only 1 or 2 ms in a single CPU thread, even when 50K correspondences are processed. This has important implications for real-time applications. What's more, we show that incorporating GMS into the classic feature matching and epipolar geometry estimation pipeline can significantly boost the overall performance. Finally, we integrate GMS into the well-known ORB-SLAM system for monocular initialization, resulting in a significant improvement. [ABSTRACT FROM AUTHOR]

Three-dimensionally (3D) knitted technical textiles are spreading into industrial applications, since their geometric, structural and functional performance can be tailored and optimized on fibre-, yarn- and fabric levels by customizing yarn materials, knit patterns and geometric shapes. The ability to simulate their complex mechanical behaviour is thus an essential ingredient in the development of a digital workflow for optimal design and manufacture of 3D knitted textiles. Here, we present a multi-scale modelling and simulation framework for the prediction of the nonlinear orthotropic mechanical behaviour of single jersey knitted textiles and its experimental validation. On the meso-scale, representative volume elements (RVEs) of the fabric are modelled as single, interlocked yarn loops and their mechanical deformation behaviour is homogenized using periodic boundary conditions. Yarns are modelled as nonlinear 3D beam elements and numerically discretized using an isogeometric collocation method, where a frictional contact formulation is used to model inter-yarn interactions. On the macro-scale, fabrics are modelled as membrane elements with nonlinear orthotropic material behaviour, which is parameterized by a response surface constitutive model obtained from the meso-scale homogenization. The input parameters of the yarn-level simulation, i.e., mechanical properties of yarns and geometric dimensions of yarn loops in the fabrics, are determined experimentally and subsequent meso- and macro-scale simulation results are evaluated against reference results and mechanical tests of knitted fabric samples. Good agreement between computational predictions and experimental results is achieved for samples with varying stitch values, thus validating our novel computational approach combining efficient meso-scale simulation using 3D beam modelling of yarns with numerical homogenization and nonlinear orthotropic response surface constitutive modelling on the macro-scale. [ABSTRACT FROM AUTHOR]

Image compositing is widely used to combine visual elements from separate source images into a single image. Although recent image compositing techniques are capable of achieving smooth blending of the visual elements from different sources, most of them implicitly assume the source images are taken in the same viewpoint. In this paper, we present an approach to compositing novel image objects from multiple source images which have different viewpoints. Our key idea is to construct 3D proxies for meaningful components of the source image objects, and use these 3D component proxies to warp and seamlessly merge components together in the same viewpoint. To realize this idea, we introduce a coordinate-frame based single-view camera calibration algorithm to handle general types of image objects, a structure-aware cuboid optimization algorithm to get the cuboid proxies for image object components with correct structure relationship, and finally a 3D-proxy transformation guided image warping algorithm to stitch object components. We further describe a novel application based on this compositing approach to automatically synthesize a large number of image objects from a set of exemplars. Experimental results show that our compositing approach can be applied to a variety of image objects, such as chairs, cups, lamps, and robots, and the synthesis application can create novel image objects with significant shape and style variations from a small set of exemplars. [ABSTRACT FROM AUTHOR]