MISS GAN: A Multi-IlluStrator Style Generative Adversarial Network for image to illustration translation

• URL: http://arxiv.org/abs/2108.05693v1
• Date: Thu, 12 Aug 2021 12:23:28 GMT
• Title: MISS GAN: A Multi-IlluStrator Style Generative Adversarial Network for image to illustration translation
• Authors: Noa Barzilay, Tal Berkovitz Shalev, Raja Giryes
• Abstract summary: Multi-IlluStrator Style Generative Adversarial Network (MISS GAN) is a framework for unsupervised image-to-illustration translation. MISS GAN is both input image specific and uses the information of other images using only one trained model.
• Score: 39.57350884615545
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unsupervised style transfer that supports diverse input styles using only one trained generator is a challenging and interesting task in computer vision. This paper proposes a Multi-IlluStrator Style Generative Adversarial Network (MISS GAN) that is a multi-style framework for unsupervised image-to-illustration translation, which can generate styled yet content preserving images. The illustrations dataset is a challenging one since it is comprised of illustrations of seven different illustrators, hence contains diverse styles. Existing methods require to train several generators (as the number of illustrators) to handle the different illustrators' styles, which limits their practical usage, or require to train an image specific network, which ignores the style information provided in other images of the illustrator. MISS GAN is both input image specific and uses the information of other images using only one trained model.

Related papers

• Ada-adapter:Fast Few-shot Style Personlization of Diffusion Model with Pre-trained Image Encoder [57.574544285878794]
  Ada-Adapter is a novel framework for few-shot style personalization of diffusion models. Our method enables efficient zero-shot style transfer utilizing a single reference image. We demonstrate the effectiveness of our approach on various artistic styles, including flat art, 3D rendering, and logo design.
  arXiv  Detail & Related papers  (2024-07-08T02:00:17Z)
• Customize StyleGAN with One Hand Sketch [0.0]
  We propose a framework to control StyleGAN imagery with a single user sketch. We learn a conditional distribution in the latent space of a pre-trained StyleGAN model via energy-based learning. Our model can generate multi-modal images semantically aligned with the input sketch.
  arXiv  Detail & Related papers  (2023-10-29T09:32:33Z)
• Learning Diverse Tone Styles for Image Retouching [73.60013618215328]
  We propose to learn diverse image retouching with normalizing flow-based architectures. A joint-training pipeline is composed of a style encoder, a conditional RetouchNet, and the image tone style normalizing flow (TSFlow) module. Our proposed method performs favorably against state-of-the-art methods and is effective in generating diverse results.
  arXiv  Detail & Related papers  (2022-07-12T09:49:21Z)
• Looks Like Magic: Transfer Learning in GANs to Generate New Card Illustrations [5.006086647446482]
  We introduce a novel dataset, named MTG, with thousands of illustration from diverse card types and rich in metadata. We show that simpler models, such as DCGANs, are not able to learn to generate proper illustrations in any setting. We perform experiments to understand how well pre-trained features from StyleGan2 can be transferred towards the target domain.
  arXiv  Detail & Related papers  (2022-05-28T14:02:09Z)
• Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning [84.8813842101747]
  Contrastive Arbitrary Style Transfer (CAST) is a new style representation learning and style transfer method via contrastive learning. Our framework consists of three key components, i.e., a multi-layer style projector for style code encoding, a domain enhancement module for effective learning of style distribution, and a generative network for image style transfer.
  arXiv  Detail & Related papers  (2022-05-19T13:11:24Z)
• StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN [17.93566359555703]
  We show that with a pretrained StyleGAN along with some operations, we can perform comparably to the state-of-the-art methods on various tasks. The proposed method is simple, effective, efficient, and applicable to any existing pretrained StyleGAN model.
  arXiv  Detail & Related papers  (2021-11-02T14:31:22Z)
• StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis [68.3787368024951]
  We propose a novel approach for multi-modal Image-to-image (I2I) translation. We learn a latent embedding, jointly with the generator, that models the variability of the output domain. Specifically, we pre-train a generic style encoder using a novel proxy task to learn an embedding of images, from arbitrary domains, into a low-dimensional style latent space.
  arXiv  Detail & Related papers  (2021-04-14T19:58:24Z)
• Generating Embroidery Patterns Using Image-to-Image Translation [2.055949720959582]
  We propose two machine learning techniques to solve the embroidery image-to-image translation. Our goal is to generate a preview image which looks similar to an embroidered image, from a user-uploaded image. Empirical results show that these techniques successfully generate an approximate preview of an embroidered version of a user image.
  arXiv  Detail & Related papers  (2020-03-05T20:32:40Z)
• P$^2$-GAN: Efficient Style Transfer Using Single Style Image [2.703193151632043]
  Style transfer is a useful image synthesis technique that can re-render given image into another artistic style. Generative Adversarial Network (GAN) is a widely adopted framework toward this task for its better representation ability on local style patterns. In this paper, a novel Patch Permutation GAN (P$2$-GAN) network that can efficiently learn the stroke style from a single style image is proposed.
  arXiv  Detail & Related papers  (2020-01-21T12:08:08Z)
• MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration [53.98437317161086]
  Given an input face photo, the goal of caricature generation is to produce stylized, exaggerated caricatures that share the same identity as the photo. We propose a novel framework called Multi-Warping GAN (MW-GAN), including a style network and a geometric network. Experiments show that caricatures generated by MW-GAN have better quality than existing methods.
  arXiv  Detail & Related papers  (2020-01-07T03:08:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.