Points acquired by laser scanners are not intrinsically equipped with normals, which are essential to surface reconstruction and point set rendering using surfels. Normal estimation is notoriously sensitive to noise. Near sharp features, the computation of noise-free normals becomes even more challenging due to the inherent undersampling problem at edge singularities. As a result, common edge-aware consolidation techniques such as bilateral smoothing may still produce erroneous normals near the edges. We propose a resampling approach to process a noisy and possibly outlier-ridden point set in an edge-aware manner. Our key idea is to first resample away from the edges so that reliable normals can be computed at the samples, and then based on reliable data, we progressively resample the point set while approaching the edge singularities. We demonstrate that our Edge-Aware Resampling (EAR) algorithm is capable of producing consolidated point This work is supported in part by grants from NSFC (61103166),

We introduce L1-medial skeleton as a curve skeleton representation for 3D point cloud data. The L1-median is well-known as a robust global center of an arbitrary set of points. We make the key observation that adapting L1-medians locally to a point set representing a 3D shape gives rise to a one-dimensional structure, which can be seen as a localized center of the shape. The primary advantage of our approach is that it does not place strong requirements on the quality of the input point cloud nor on the geometry or topology of the captured shape. We develop a L1-medial skeleton construction algorithm, which can be directly applied to an unoriented raw point scan with significant noise, outliers, and large areas of missing data. We demonstrate L1-medial skeletons extracted from raw scans of a variety of shapes, including those modeling high-genus 3D objects, plant-like structures, and curve networks.

Figure 1: We develop a deep neural network for 3D point set upsampling. Intuitively, our network learns different levels of detail in multiple steps, where each step focuses on a local patch from the output of the previous step. By progressively training our patch-based network end-to-end, we successfully upsample a sparse set of input points, step by step, to a dense point set with rich geometric details. Here we use circle plates for points rendering, which are color-coded by point normals. AbstractWe present a detail-driven deep neural network for point set upsampling. A high-resolution point set is essential for point-based rendering and surface reconstruction. Inspired by the recent success of neural image super-resolution techniques, we progressively train a cascade of patch-based upsampling networks on different levels of detail end-to-end. We propose a series of architectural design contributions that lead to a substantial performance boost. The effect of each technical contribution is demonstrated in an ablation study. Qualitative and quantitative experiments show that our method significantly outperforms the state-of-theart learning-based [58,59], and optimazation-based [23] approaches, both in terms of handling low-resolution inputs and revealing high-fidelity details. The data and code are at https://github.com/yifita/3pu.

Fig. 1. Using our differentiable point-based renderer, scene content can be optimized to match target rendering. Here, the positions and normals of points are optimized in order to reproduce the reference rendering of the Stanford bunny. It successfully deforms a sphere to a target bunny model, capturing both large scale and fine-scale structures. From left to right are the input points, the results of iteration 18, 57, 198, 300, and the target.We propose Differentiable Surface Splatting (DSS), a high-fidelity differentiable renderer for point clouds. Gradients for point locations and normals are carefully designed to handle discontinuities of the rendering function. Regularization terms are introduced to ensure uniform distribution of the points on the underlying surface. We demonstrate applications of DSS to inverse rendering for geometry synthesis and denoising, where large scale topological changes, as well as small scale detail modifications, are accurately and robustly handled without requiring explicit connectivity, outperforming state-of-the-art techniques. The data and code are at https://github.com/yifita/DSS.

Fig. 1. Our stretch-sensing soft glove captures hand poses in real time and with high accuracy. It functions in diverse and challenging settings, like heavily occluded environments or changing light conditions, and lends itself to various applications. All images shown here are frames from recorded live sessions. We propose a stretch-sensing soft glove to interactively capture hand poses with high accuracy and without requiring an external optical setup. We demonstrate how our device can be fabricated and calibrated at low cost, using simple tools available in most fabrication labs. To reconstruct the pose from the capacitive sensors embedded in the glove, we propose a deep network architecture that exploits the spatial layout of the sensor itself. The network is trained only once, using an inexpensive off-the-shelf hand pose reconstruction system to gather the training data. The per-user calibration is then performed on-the-fly using only the glove. The glove's capabilities are demonstrated in a series of ablative experiments, exploring different models and calibration methods. Comparing against commercial data gloves, we achieve a 35% improvement in reconstruction accuracy.

Chondrocyte apoptosis is an important mechanism involved in osteoarthritis (OA). Berberine (BBR), a plant alkaloid derived from Chinese medicine, is characterized by multiple pharmacological effects, such as anti-inflammatory and anti-apoptotic activities. This study aimed to evaluate the chondroprotective effect and underlying mechanisms of BBR on sodium nitroprusside (SNP)-stimulated chondrocyte apoptosis and surgically-induced rat OA model. The in vitro results revealed that BBR suppressed SNP-stimulated chondrocyte apoptosis as well as cytoskeletal remodeling, down-regulated expressions of inducible nitric oxide synthase (iNOS) and caspase-3, and up-regulated Bcl-2/Bax ratio and Type II collagen (Col II) at protein levels, which were accompanied by increased adenosine monophosphate-activated protein kinase (AMPK) phosphorylation and decreased phosphorylation of p38 mitogen-activated protein kinase (MAPK). Furthermore, the anti-apoptotic effect of BBR was blocked by AMPK inhibitor Compound C (CC) and adenosine-9-β-D-arabino-furanoside (Ara A), and enhanced by p38 MAPK inhibitor SB203580. In vivo experiment suggested that BBR ameliorated cartilage degeneration and exhibited an anti-apoptotic effect on articular cartilage in a rat OA model, as demonstrated by histological analyses, TUNEL assay and immunohistochemical analyses of caspase-3, Bcl-2 and Bax expressions. These findings suggest that BBR suppresses SNP-stimulated chondrocyte apoptosis and ameliorates cartilage degeneration via activating AMPK signaling and suppressing p38 MAPK activity.

In this paper, we present a consolidation method that is based on a new representation of 3D point sets. The key idea is to augment each surface point into a deep point by associating it with an inner point that resides on the meso-skeleton, which consists of a mixture of skeletal curves and sheets. The deep points representation is a result of a joint optimization applied to both ends of the deep points. The optimization objective is to fairly distribute the end points across the surface and the meso-skeleton, such that the deep point orientations agree with the surface normals. The optimization converges where the inner points form a coherent meso-skeleton, and the surface points are consolidated with the missing regions completed. The strength of this new representation stems from the fact that it is comprised of both local and non-local geometric information. We demonstrate the advantages of the deep points consolidation technique by employing it to consolidate and complete noisy point-sampled geometry with large missing parts.

Figure 1: Our robot-based, Poisson-guided autoscanner can progressively, adaptively, and fully automatically generate complete, high quality, and high fidelity scan models. AbstractWe present a quality-driven, Poisson-guided autonomous scanning method. Unlike previous scan planning techniques, we do not aim to minimize the number of scans needed to cover the object's surface, but rather to ensure the high quality scanning of the model. This goal is achieved by placing the scanner at strategically selected Next-Best-Views (NBVs) to ensure progressively capturing the geometric details of the object, until both completeness and high fidelity are reached. The technique is based on the analysis of a Poisson field and its geometric relation with an input scan. We generate a confidence map that reflects the quality/fidelity of the estimated Poisson iso-surface. The confidence map guides the generation of a viewing vector field, which is then used for computing a set of NBVs. We applied the algorithm on two different robotic platforms, a PR2 mobile robot and a one-arm industry robot. We demonstrated the advantages of our method through a number of autonomous high quality scannings of complex physical objects, as well as performance comparisons against state-of-the-art methods.