3篇
您的检索式：作者名="Wanquan Feng"
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | 2D and 3D orientation mapping in nanostructured metals: A review显示文摘Nanostructured metals possess various excellent properties and offer the potential for a wide range of applications.Improvements in the properties and performance of nanostructured metal components motivate a complete characterization of the microstructures and crystallographic orientations of nanostructured metals with nanoscale spatial resolution.Two well developed orientation mapping techniques for such characterization are electron backscatter diffraction(EBSD)in the scanning electron microscope and precession electron diffraction(PED)using diffraction spots in the transmission electron microscope.However,these methods can only characterize the structure in two dimensions.It is still a great challenge to characterize grains in three dimensions,i.e.from the interior of the nanostructured metals.Recently,three-dimensional orientation mapping in the transmission electron microscope(3 D-OMi TEM)was developed and further improvements of this technique are introduced in this paper.Utilization of these orientation mapping techniques for structural and orientational characterizations are demonstrated by examples of surface-deformed metals with gradient nanostructures,and a sputtered gold film of nano-islands containing nanograins.The merits and challenges of each of these techniques are discussed and suggestions for further developments are proposed. | Guilin Wu Wanquan Zhu Qiongyao He Zongqiang Feng Tianlin Huang Ling Zhang SØren Schmidt Andrew Godfrey Xiaoxu Huang | 2020 | Nano Materials Science2020，2，1： | 1 |
| 2 | Differentiable Deformation Graph-Based Neural Non-rigid Registration显示文摘The traditional pipeline for non-rigid registration is to iteratively update the correspondence and alignment such that the transformed source surface aligns well with the target surface.Among the pipeline,the correspondence construction and iterative manner are key to the results,while existing strategies might result in local optima.In this paper,we adopt the widely used deformation graph-based representation,while replacing some key modules with neural learning-based strategies.Specifically,we design a neural network to predict the correspondence and its reliability confidence rather than the strategies like nearest neighbor search and pair rejection.Besides,we adopt the GRU-based recurrent network for iterative refinement,which is more robust than the traditional strategy.The model is trained in a self-supervised manner and thus can be used for arbitrary datasets without ground-truth.Extensive experiments demonstrate that our proposed method outperforms the state-of-the-art methods by a large margin. | Wanquan Feng Hongrui Cai Junhui Hou Bailin Deng Juyong Zhang | 2023 | Communications in Mathematics and Statistics2023，11，1： | 0 |
| 3 | Facial optical flow estimation via neural non-rigid registration显示文摘Optical flow estimation in human facial video,which provides 2D correspondences between adjacent frames,is a fundamental pre-processing step for many applications,like facial expression capture and recognition.However,it is quite challenging as human facial images contain large areas of similar textures,rich expressions,and large rotations.These characteristics also result in the scarcity of large,annotated realworld datasets.We propose a robust and accurate method to learn facial optical flow in a self-supervised manner.Specifically,we utilize various shape priors,including face depth,landmarks,and parsing,to guide the self-supervised learning task via a differentiable nonrigid registration framework.Extensive experiments demonstrate that our method achieves remarkable improvements for facial optical flow estimation in the presence of significant expressions and large rotations. | Zhuang Peng Boyi Jiang Haofei Xu Wanquan Feng Juyong Zhang | 2023 | Computational Visual Media2023，9，1： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员