Fast Learning of Signed Distance Functions From Noisy Point Clouds Via Noise to Noise Mapping.

Learning signed distance functions (SDFs) from point clouds is an important task in 3D computer vision. However, without ground truth signed distances, point normals or clean point clouds, current methods still struggle from learning SDFs from noisy point clouds. To overcome this challenge, we propose to learn SDFs via a noise to noise mapping, which does not require any clean point cloud or ground truth supervision. Our novelty lies in the noise to noise mapping which can infer a highly accurate SDF of a single object or scene from its multiple or even single noisy observations. We achieve this by a novel loss which enables statistical reasoning on point clouds and maintains geometric consistency although point clouds are irregular, unordered and have no point correspondence among noisy observations. To accelerate training, we use multi-resolution hash encodings implemented in CUDA in our framework, which reduces our training time by a factor of ten, achieving convergence within one minute. We further introduce a novel schema to improve multi-view reconstruction by estimating SDFs as a prior. Our evaluations under widely-used benchmarks demonstrate our superiority over the state-of-the-art methods in surface reconstruction from point clouds or multi-view images, point cloud denoising and upsampling.

CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization.

Surface reconstruction for point clouds is an important task in 3D computer vision. Most of the latest methods resolve this problem by learning signed distance functions from point clouds, which are limited to reconstructing closed surfaces. Some other methods tried to represent open surfaces using unsigned distance functions (UDF) which are learned from ground truth distances. However, the learned UDF is hard to provide smooth distance fields due to the discontinuous character of point clouds. In this paper, we propose CAP-UDF, a novel method to learn consistency-aware UDF from raw point clouds. We achieve this by learning to move queries onto the surface with a field consistency constraint, where we also enable to progressively estimate a more accurate surface. Specifically, we train a neural network to gradually infer the relationship between queries and the approximated surface by searching for the moving target of queries in a dynamic way. Meanwhile, we introduce a polygonization algorithm to extract surfaces using the gradients of the learned UDF. We conduct comprehensive experiments in surface reconstruction for point clouds, real scans or depth maps, and further explore our performance in unsupervised point normal estimation, which demonstrate non-trivial improvements of CAP-UDF over the state-of-the-art methods.

Topical Delivery of Levocarnitine to the Cornea and Anterior Eye by Thermosensitive in-situ Gel for Dry Eye Disease.

PURPOSE: To prepare the levocarnitine thermosensitive in situ gel (LCTG) and evaluate its effect on dry eye disease (DED). METHODS: Draize eye irritation test and other examinations were used to evaluate the eye irritation after multiple administration of LCTG. The Schirmer test, fluorescein sodium staining, HE staining and TUNEL staining were used to detect the tear secretion, corneal injury, histopathological changes of the cornea and lacrimal gland, and the apoptosis rate of cornea epithelial cells after 3 days of the administration. The conjunctival goblet cell density was detected by PAS staining, and the expression levels of matrix metalloproteinase-3 (MMP-3) and matrix metalloproteinase-9 (MMP-9) of corneal epithelial cells were detected by immunofluorescence staining after 7 days of the administration. RESULTS: LCTG is non-irritating to rabbit eyes and has good biocompatibility. LCTG administration for 3 days can significantly increase the amount of tear secretion in mice with DED, promote corneal epithelial integrity and central corneal epithelium thickness recovery, and improve the pathological morphology and structure of corneal and lacrimal gland tissues, and reduce the apoptosis rate of the corneal epithelial cells. After 7 days of the administration, the preparation can promote the proliferation of conjunctival goblet cells and down-regulate the cornea expression levels of MMP-3 and MMP-9 in epithelial cells. CONCLUSION: The LCTG has a good curative effect on mice with DED, and the overall curative effect is better than that of levocarnitine solution.

A Systematic Review of the Pharmacology, Toxicology and Pharmacokinetics of Matrine.

Matrine (MT) is a naturally occurring alkaloid and an bioactive component of Chinese herbs, such as Sophora flavescens and Radix Sophorae tonkinensis. Emerging evidence suggests that MT possesses anti-cancer, anti-inflammatory, anti-oxidant, antiviral, antimicrobial, anti-fibrotic, anti-allergic, antinociceptive, hepatoprotective, cardioprotective, and neuroprotective properties. These pharmacological properties form the foundation for its application in the treatment of various diseases, such as multiple types of cancers, hepatitis, skin diseases, allergic asthma, diabetic cardiomyopathy, pain, Alzheimer's disease (AD), Parkinson's disease (PD), and central nervous system (CNS) inflammation. However, an increasing number of published studies indicate that MT has serious adverse effects, the most obvious being liver toxicity and neurotoxicity, which are major factors limiting its clinical use. Pharmacokinetic studies have shown that MT has low oral bioavailability and short half-life in vivo. This review summarizes the latest advances in research on the pharmacology, toxicology, and pharmacokinetics of MT, with a focus on its biological properties and mechanism of action. The review provides insight into the future of research on traditional Chinese medicine.

Reconstructing 3D Shapes from Multiple Sketches using Direct Shape Optimization.

3D shape reconstruction from multiple hand-drawn sketches is an intriguing way to 3D shape modeling. Currently, state-of-the-art methods employ neural networks to learn a mapping from multiple sketches from arbitrary view angles to a 3D voxel grid. Because of the cubic complexity of 3D voxel grids, however, neural networks are hard to train and limited to low resolution reconstructions, which leads to a lack of geometric detail and low accuracy. To resolve this issue, we propose to reconstruct 3D shapes from multiple sketches using direct shape optimization (DSO), which does not involve deep learning models for direct voxel-based 3D shape generation. Specifically, we first leverage a conditional generative adversarial network (CGAN) to translate each sketch into an attenuance image that captures the predicted geometry from a given viewpoint. Then, DSO minimizes a project-and-compare loss to reconstruct the 3D shape such that it matches the predicted attenuance images from the view angles of all input sketches. Based on this, we further propose a progressive update approach to handle inconsistencies among a few hand-drawn sketches for the same 3D shape. Our experimental results show that our method significantly outperforms the state-of-the-art methods under widely used benchmarks and produces intuitive results in an interactive application.

Polygonum multiflorum-Induced Liver Injury: Clinical Characteristics, Risk Factors, Material Basis, Action Mechanism and Current Challenges.

Polygonum multiflorum Thunb. (PM), called Heshouwu in China, is a popular Chinese medicine in clinical practice. Several clinical studies have been conducted to evaluate the traditional therapeutic claims and to study the potential therapeutic activity of PM in dyslipidemia and neurodegenerative diseases, highlighting available clinical evidence. In recent years, reports on clinical adverse reactions of Raw Radix P. multiflorum (RPM) and P. multiflorum Praeparata (PMP) have been on the increase, especially with respect to liver injury. Most liver injury cases had been assessed for causality using RUCAM (Roussel Uclaf Causality Assessment Method) in this paper. However, the components of PM responsible for the reported hepatotoxic effects have not yet been identified. Moreover, many of the reports are contradictory, while studies on the mechanism involved in PM-induced liver damage are not comprehensive. This study was aimed at reviewing the status of research on liver injury due to PM, including clinical characteristics, risk factors, material basis research and mechanism of action, with a view to understanding PM-induced hepatotoxicity, and taking reasonable and effective measures to prevent it. In short, quality control is still one of the major safety problems in TCM drug safety concerns. The model of safety monitoring and risk management of PM drugs is not yet developed. Indeed, the characteristics and risk factors associated with PM require both proper understanding and control of the risk by strengthening standardization of clinical applications, basic science research, quality control in manufacturing, active monitoring methodology and enhancement of international communication and cooperation. Measures should also be encouraged and implemented to promote healthy development of the TCM industry.