Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
arXiv:1901.03447
Abstract
This paper addresses the problem of interpolating visual textures. We formulate this problem by requiring (1) by-example controllability and (2) realistic and smooth interpolation among an arbitrary number of texture samples. To solve it we propose a neural network trained simultaneously on a reconstruction task and a generation task, which can project texture examples onto a latent space where they can be linearly interpolated and projected back onto the image domain, thus ensuring both intuitive control and realistic results. We show our method outperforms a number of baselines according to a comprehensive suite of metrics as well as a user study. We further show several applications based on our technique, which include texture brush, texture dissolve, and animal hybridization.
arXiv commentAccepted to CVPR'19
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Toward Multimodal Image-to-Image Translation
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
- Generative Image Inpainting with Contextual Attention
- Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses
- Non-Stationary Texture Synthesis by Adversarial Expansion
- Demystifying MMD GANs
- Texture Synthesis with Spatial Generative Adversarial Networks
- StyleBank: An Explicit Representation for Neural Image Style Transfer