Unsupervised 3D Reconstruction with Multi-Measure and High-Resolution Loss.

Multi-view 3D reconstruction technology based on deep learning is developing rapidly. Unsupervised learning has become a research hotspot because it does not need ground truth labels. The current unsupervised method mainly uses 3DCNN to regularize the cost volume to regression image depth. This approach results in high memory requirements and long computing time. In this paper, we propose an end-to-end unsupervised multi-view 3D reconstruction network framework based on PatchMatch, Unsup_patchmatchnet. It dramatically reduces memory requirements and computing time. We propose a feature point consistency loss function. We incorporate various self-supervised signals such as photometric consistency loss and semantic consistency loss into the loss function. At the same time, we propose a high-resolution loss method. This improves the reconstruction of high-resolution images. The experiment proves that the memory usage of the network is reduced by 80% and the running time is reduced by more than 50% compared with the network using 3DCNN method. The overall error of reconstructed 3D point cloud is only 0.501 mm. It is superior to most current unsupervised multi-view 3D reconstruction networks. Then, we test on different data sets and verify that the network has good generalization.

G2O-Pose: Real-Time Monocular 3D Human Pose Estimation Based on General Graph Optimization.

Monocular 3D human pose estimation is used to calculate a 3D human pose from monocular images or videos. It still faces some challenges due to the lack of depth information. Traditional methods have tried to disambiguate it by building a pose dictionary or using temporal information, but these methods are too slow for real-time application. In this paper, we propose a real-time method named G2O-pose, which has a high running speed without affecting the accuracy so much. In our work, we regard the 3D human pose as a graph, and solve the problem by general graph optimization (G2O) under multiple constraints. The constraints are implemented by algorithms including 3D bone proportion recovery, human orientation classification and reverse joint correction and suppression. When the depth of the human body does not change much, our method outperforms the previous non-deep learning methods in terms of running speed, with only a slight decrease in accuracy.

Utilization of deep eutectic solvent as a degumming protocol for raw silk: Towards performance and mechanism elucidation.

Degumming is the most critical step for the silk textile industry and the process of silk-based advanced materials. However, current common degumming techniques are largely limited because of insufficient efficiency, obvious hydrolysis damage and difficulty in long-term storage. Here, deep eutectic solvent (DES) constituted of choline chloride (ChCl) and urea was explored to Bombyx mori silk fibers degumming without combining any further treatment. Compared to traditional alkali methods, DES could quickly remove about 26.5 % of sericin in just 40 min, and its degumming efficiency hardly decrease after seven cycles. Owing to the "tear off" degumming mechanism of DES molecules with "large volume", the resulted sericin has a large molecular weight of 250 kDa. In addition, because of antibacterial activity and stabilizing effect, no aggregation occurred and strong bacterial growth inhibition was triggered in the obtained sericin/DES solution. Furthermore, thanks to the good retention of crystalline region and slight swelling of amorphous area, the sericin-free fibroin showed significant increases in moisture absorption and dye uptake, while maintaining good mechanical properties. Featured with high efficiency, reduction in water pollution, easy storage of sericin as well as high quality fibers, this approach is of great potential for silk wet processing.