Be Your Own Prada: Fashion Synthesis with Structural Coherence

@article{Zhu2017BeYO,
  title={Be Your Own Prada: Fashion Synthesis with Structural Coherence},
  author={Shizhan Zhu and Sanja Fidler and Raquel Urtasun and Dahua Lin and Chen Change Loy},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1689-1697}
}
We present a novel and effective approach for generating new clothing on a wearer through generative adversarial learning. [] Key Method In the second stage, a generative model with a newly proposed compositional mapping layer is used to render the final image with precise regions and textures conditioned on this map. We extended the DeepFashion dataset [8] by collecting sentence descriptions for 79K images. We demonstrate the effectiveness of our approach through both quantitative and qualitative…
Pose Guided Fashion Image Synthesis Using Deep Generative Model
TLDR
This paper presents a novel deep generative model to transfer an image of a person from a given pose to a new pose while keeping fashion item consistent and demonstrates the results by conducting rigorous experiments on two data sets.
Unsupervised Person Image Synthesis in Arbitrary Poses
TLDR
A novel approach for synthesizing photorealistic images of people in arbitrary poses using generative adversarial learning, which considers a pose conditioned bidirectional generator that maps back the initially rendered image to the original pose, hence being directly comparable to the input image without the need to resort to any training image.
FACT: Fused Attention for Clothing Transfer with Generative Adversarial Networks
TLDR
A novel semantic-based Fused Attention model for Clothing Transfer (FACT), which allows fine-grained synthesis, high global consistency and plausible hallucination in images, and develops a stylized channel-wise attention module to capture correlations on feature levels.
Unpaired Pose Guided Human Image Generation
TLDR
An end-to-end trainable network under the generative adversarial framework is proposed that provides detailed control over the final appearance while not requiring paired training data and hence allows us to forgo the challenging problem of fitting 3D poses to 2D images.
GANimation: Anatomically-aware Facial Animation from a Single Image
TLDR
A novel GAN conditioning scheme based on Action Units (AU) annotations, which describes in a continuous manifold the anatomical facial movements defining a human expression, and proposes a fully unsupervised strategy to train the model, that only requires images annotated with their activated AUs.
Style-Controlled Synthesis of Clothing Segments for Fashion Image Manipulation
TLDR
This work proposes an approach for digitally altering people's outfits in images by generating a new clothing item image that displays the color and pattern of the desired style while geometrically mimicking the person's original item.
ClothFlow: A Flow-Based Model for Clothed Person Generation
TLDR
ClothFlow is presented, an appearance-flow-based generative model to synthesize clothed person for posed-guided person image generation and virtual try-on and strong qualitative and quantitative results validate the effectiveness of the method.
Text to Image Generation of Fashion Clothing
TLDR
This paper proposes an approach a framework that will accept text input from the user about the fashion pattern and the model will generate images of fashion clothing based on the text input, which can assist people be their own designers for creating a range offashion clothing for themselves using the power of Deep Learning and Generative Adversarial Networks.
TailorGAN: Making User-Defined Fashion Designs
TLDR
A novel self-supervised model to synthesize garment images with disentangled attributes (e.g., collar and sleeves) without paired data is proposed and can synthesize much better results than the state-of-the-art methods in both quantitative and qualitative comparisons.
SwapGAN: A Multistage Generative Approach for Person-to-Person Fashion Style Transfer
TLDR
This paper proposes a multistage deep generative approach named SwapGAN that exploits three generators and one discriminator in a unified framework to fulfill the task end-to-end and demonstrates the improvements of SwapGAN over other existing approaches through both quantitative and qualitative evaluations.
...
...

References

SHOWING 1-10 OF 21 REFERENCES
Generative Image Modeling Using Style and Structure Adversarial Networks
TLDR
This paper factorize the image generation process and proposes Style and Structure Generative Adversarial Network, a model that is interpretable, generates more realistic images and can be used to learn unsupervised RGBD representations.
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
TLDR
This paper proposes Stacked Generative Adversarial Networks (StackGAN) to generate 256 photo-realistic images conditioned on text descriptions and introduces a novel Conditioning Augmentation technique that encourages smoothness in the latent conditioning manifold.
Generative Adversarial Text to Image Synthesis
TLDR
A novel deep architecture and GAN formulation is developed to effectively bridge advances in text and image modeling, translating visual concepts from characters to pixels.
Detailed Garment Recovery from a Single-View Image
TLDR
This work proposes a method that is able to compute a rich and realistic 3D model of a human body and its outfits from a single photograph with little human involvement, and demonstrates the effectiveness of the algorithm by re-purposing the reconstructed garments for virtual try-on and garment transfer applications, as well as cloth animation for digital characters.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
TLDR
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.
Image-to-Image Translation with Conditional Adversarial Networks
TLDR
Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
Contextual Action Recognition with R*CNN
TLDR
This work exploits the simple observation that actions are accompanied by contextual cues to build a strong action recognition system and adapt RCNN to use more than one region for classification while still maintaining the ability to localize the action.
DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations
TLDR
This work introduces DeepFashion1, a large-scale clothes dataset with comprehensive annotations, and proposes a new deep model, namely FashionNet, which learns clothing features by jointly predicting clothing attributes and landmarks.
Improved Techniques for Training GANs
TLDR
This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes.
Pixel-Level Domain Transfer
TLDR
The model transfers an input domain to a target domain in semantic level, and generates the target image in pixel level and employs the real/fake-discriminator as in Generative Adversarial Nets to generate realistic target images.
...
...