English

CNN based texture synthesize with Semantic segment

Computer Vision and Pattern Recognition 2016-05-17 v1 Graphics Machine Learning

Abstract

Deep learning algorithm display powerful ability in Computer Vision area, in recent year, the CNN has been applied to solve problems in the subarea of Image-generating, which has been widely applied in areas such as photo editing, image design, computer animation, real-time rendering for large scale of scenes and for visual effects in movies. However in the texture synthesize procedure. The state-of-art CNN can not capture the spatial location of texture in image, lead to significant distortion after texture synthesize, we propose a new way to generating-image by adding the semantic segment step with deep learning algorithm as Pre-Processing and analyze the outcome.

Keywords

Cite

@article{arxiv.1605.04731,
  title  = {CNN based texture synthesize with Semantic segment},
  author = {Xianye Liang and Bocheng Zhuo and Peijie Li and Liangju He},
  journal= {arXiv preprint arXiv:1605.04731},
  year   = {2016}
}

Comments

7 pages, 4 figures. arXiv admin note: text overlap with arXiv:1505.07376, arXiv:1604.04339, arXiv:1602.07188 by other authors

R2 v1 2026-06-22T14:01:34.999Z