It is implemented by making full usage of preceding super-resolved frames and a temporal window of adjacent low-resolution frames. Taking advantage of high inter-frame dependency in videos, we propose a self-enhanced convolutional network for facial video hallucination. However, the direct migration of existing methods to video is still difficult to achieve good performance due to its lack of alignment and consistency modelling in temporal domain. IEEE Transactions on Image Processing, Vol 29, 2020Īs a domain-specific super-resolution problem, facial image hallucination has enjoyed a series of breakthroughs thanks to the advances of deep convolutional neural networks. Self-Enhanced Convolutional Network for Facial Video HallucinationĬhaowei Fang, Guanbin Li, Xiaoguang Han, and Yizhou Yu A list of papers discussed in this review, corresponding codes, pre-trained models and more comparison results are publicly available at. The review concludes with a discussion of various applications of NST and open problems for future research. Then, we present several evaluation methods and compare different NST algorithms both qualitatively and quantitatively. We first propose a taxonomy of current algorithms in the field of NST. In this paper, we aim to provide a comprehensive overview of the current progress towards NST. It is receiving increasing attention and a variety of approaches are proposed to either improve or extend the original NST algorithm. ![]() Since then, NST has become a trending topic both in academic literature and industrial applications. ![]() This process of using CNNs to render a content image in different styles is referred to as Neural Style Transfer (NST). demonstrated the power of Convolutional Neural Networks (CNNs) in creating artistic imagery by separating and recombining image content and style. IEEE Transactions on Visualizationa and Computer Graphics, Vol 26, No 11, 2020, Yongcheng Jing, Yezhou Yang, Zunlei Feng, Jingwen Ye, Yizhou Yu, and Mingli Song Edge-Aware Smoothing, Intrinsic Image Decomposition, L1 Sparsity Model Image and Video Computing
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |