Augmented Coarse-to-Fine Video Frame Synthesis with Semantic Loss

摘要：

　　Existing video frame synthesis works suffer from improving perceptual quality and preserving semantic representation ability.In this paper,we propose a Progressive Motion-texture Synthesis Network(PMSN)to address this problem.Instead of learning synthesis from scratch,we introduce augmented inputs to compensate texture details and motion information.Specifically,a coarse-to-fine guidance scheme with a well-designed semantic loss is presented to improve the capability of video frame synthesis.As shown in the experiments,our proposed PMSN promises excellent quantitative results,visual effects,and generalization ability compared with traditional solutions.

关键词： Video frame synthesis Augmented input Coarse-to-fine guidance scheme Semantic loss

作者: Xin Jin Zhibo Chen Sen Liu Wei Zhou

作者单位: CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System,University of Science and Technology of China,Hefei 230027,China

会议类型: 国际会议

会议名称: 中国模式识别与计算机视觉大会(PRCV2018)

会议地点: 广州

会议语种:英文

页码: 439-452

在线出版日期: 2018-11-23（万方平台首次上网日期，不代表论文的发表时间）