Compatible and Diverse Fashion Image Inpainting
arXiv:1902.01096
Abstract
Visual compatibility is critical for fashion analysis, yet is missing in existing fashion image synthesis systems. In this paper, we propose to explicitly model visual compatibility through fashion image inpainting. To this end, we present Fashion Inpainting Networks (FiNet), a two-stage image-to-image generation framework that is able to perform compatible and diverse inpainting. Disentangling the generation of shape and appearance to ensure photorealistic results, our framework consists of a shape generation network and an appearance generation network. More importantly, for each generation network, we introduce two encoders interacting with one another to learn latent code in a shared compatibility space. The latent representations are jointly optimized with the corresponding generation network to condition the synthesis process, encouraging a diverse set of generated results that are visually compatible with existing fashion garments. In addition, our framework is readily extended to clothing reconstruction and fashion transfer, with impressive results. Extensive experiments with comparisons with state-of-the-art approaches on fashion synthesis task quantitatively and qualitatively demonstrate the effectiveness of our method.
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Distributed Representations of Words and Phrases and their Compositionality
- Conditional Generative Adversarial Nets
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Generative Adversarial Text to Image Synthesis
- Conditional Image Synthesis With Auxiliary Classifier GANs
- DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
- Fashion-Gen: The Generative Fashion Dataset and Challenge
- Language Guided Fashion Image Manipulation with Feature-wise Transformations
- Disentangling Multiple Conditional Inputs in GANs
Cited by in corpus (5)
- Toward Accurate and Realistic Virtual Try-on Through Shape Matching and Multiple Warps
- Semantically Multi-modal Image Synthesis
- ReGO: Reference-Guided Outpainting for Scenery Image
- Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing
- Toward Accurate and Realistic Outfits Visualization with Attention to Details