CNN based texture synthesize with Semantic segment
arXiv:1605.04731
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.
arXiv comment7 pages, 4 figures. arXiv admin note: text overlap with arXiv:1505.07376, arXiv:1604.04339, arXiv:1602.07188 by other authors
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Conditional Random Fields as Recurrent Neural Networks
- Going Deeper with Convolutions
- OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
- DRAW: A Recurrent Neural Network For Image Generation
- Fully Convolutional Networks for Semantic Segmentation
- Learning Deconvolution Network for Semantic Segmentation
- Identity Mappings in Deep Residual Networks
- Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks
- Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection