No abstract

We propose a novel end-to-end semi-supervised adversarial framework to generate photorealistic face images of new identities with wide ranges of expressions, poses, and illuminations conditioned by a 3D morphable model. Previous adversarial style-transfer methods either supervise their networks with large volume of paired data or use unpaired data with a highly under-constrained two-way generative framework in an unsupervised fashion. We introduce pairwise adversarial supervision to constrain two-way domain adaptation by a small number of paired real and synthetic images for training along with the large volume of unpaired data. Extensive qualitative and quantitative experiments are performed to validate our idea. Generated face images of new identities contain pose, lighting and expression diversity and qualitative results show that they are highly constraint by the synthetic input image while adding photorealism and retaining identity information. We combine face images generated by the proposed method with the real data set to train face recognition algorithms. We evaluated the model on two challenging data sets: LFW and IJB-A. We observe that the generated images from our framework consistently improves over the performance of deep face recognition network trained with Oxford VGG Face dataset and achieves comparable results to the state-of-the-art.

This paper presents a comparative study on organometal halide perovskite based solar cells using two different transparent conducting oxides such as TiO2 and ZnO as electron transporting materials. Simulation is an interesting tool for studying the behavior of every component of a solar cell device as well as for analyzing the performance of the full device. Solar cell capacitance simulator (SCAPS)‐1D has been the tool used for numerical simulation of such devices. Influences of thickness of absorber and ETMs, interface trap density of states and dopant concentration of ETMs on the performance of photovoltaic solar cells are studied. Comparable efficiencies of 22.35% and 22.49% for PV devices made of spiro‐MeOTAD/MAPbI3/TiO2 and spiro‐MeOTAD/MAPbI3/ZnO, respectively, with 400/400/90 nm thicknesses under 1 Sun illumination are observed. The performance of both devices indicates the replacement of the TiO2 by a ZnO layer. It could be a good option to reduce the cost and increase the mobility of ETM for this type of solar cells. Generally, increase in thickness of MAPbI3 perovskite up to around 700 nm results into increase in the power conversion efficiency (PCE) of the solar cells. On the other hand, TiO2 and ZnO layers thicker than 90 nm results into decrease in the efficiency of the devices. Furthermore, the increase in interface trap density is found to reduce the efficiency of the devices. (© 2015 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)

No abstract