Learning to Synthesize Fashion Textures
arXiv:1911.07472
Abstract
Existing unconditional generative models mainly focus on modeling general objects, such as faces and indoor scenes. Fashion textures, another important type of visual elements around us, have not been extensively studied. In this work, we propose an effective generative model for fashion textures and also comprehensively investigate the key components involved: internal representation, latent space sampling and the generator architecture. We use Gram matrix as a suitable internal representation for modeling realistic fashion textures, and further design two dedicated modules for modulating Gram matrix into a low-dimension vector. Since fashion textures are scale-dependent, we propose a recursive auto-encoder to capture the dependency between multiple granularity levels of texture feature. Another important observation is that fashion textures are multi-modal. We fit and sample from a Gaussian mixture model in the latent space to improve the diversity of the generated textures. Extensive experiments demonstrate that our approach is capable of synthesizing more realistic and diverse fashion textures over other state-of-the-art methods.
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Spectral Normalization for Generative Adversarial Networks
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Improved Training of Wasserstein GANs
- Improved Techniques for Training GANs
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
- Texture Synthesis Using Convolutional Neural Networks
- Wasserstein Auto-Encoders
- Texture Synthesis with Spatial Generative Adversarial Networks
- Diagnosing and Enhancing VAE Models
- Be Your Own Prada: Fashion Synthesis with Structural Coherence
- Incorporating long-range consistency in CNN-based texture generation
- Fashioning with Networks: Neural Style Transfer to Design Clothes
- Statistically Motivated Second Order Pooling