Augmented coarse-to-fine video frame synthesis with semantic loss

Jin, Xin, Chen, Zhibo, Liu, Sen and Zhou, Wei 2018. Augmented coarse-to-fine video frame synthesis with semantic loss. Presented at: Pattern Recognition and Computer Vision, PRCV 2018, Guangzhou, China, 23-26 November. Published in: Lai, Jian-Huang, Liu, Cheng-Lin, Chen, LaXilin, Zhou, Jie, Tan, Tieniu, Zheng, Nanning and Zha, Hongbin eds. Pattern Recognition and Computer Vision, First Chinese Conference, PRCV 2018, Guangzhou, China, November 23-26, 2018, Proceedings, Part I. Lecture Notes in Computer Science. Lecture Notes in Computer Science Springer, pp. 439-452. 10.1007/978-3-030-03398-9_38

Full text not available from this repository.

Abstract

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.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Springer
ISBN:	978-3-030-03397-2
ISSN:	0302-9743
Last Modified:	23 Aug 2023 16:30
URI:	https://orca.cardiff.ac.uk/id/eprint/161671

Actions (repository staff only)

Edit Item