• Corpus ID: 235606442

Fine-Tuning StyleGAN2 For Cartoon Face Generation

  title={Fine-Tuning StyleGAN2 For Cartoon Face Generation},
  author={Jihye Back},
  • Jihye Back
  • Published 22 June 2021
  • Computer Science
  • ArXiv
Recent studies have shown remarkable success in the unsupervised image to image (I2I) translation. However, due to the imbalance in the data, learning joint distribution for various domains is still very challenging. Although existing models can generate realistic target images, it’s difficult to maintain the structure of the source image. In addition, training a generative model on large data in multiple domains requires a lot of time and computer resources. To address these limitations, we… 

Figures from this paper

Face Generation and Editing with StyleGAN: A Survey

This survey focuses on GAN-based architectures that have culminated in the StyleGAN approaches, which allow generation of high-quality face images and offer rich interfaces for controllable semantics editing and preserving photo quality.

3D Cartoon Face Generation with Controllable Expressions from a Single GAN Image

The semantic meanings of StyleGAN latent space are discovered, such that face images of various expressions, poses, and lighting are able to be produced by controlling the latent codes.

Looks Like Magic: Transfer Learning in GANs to Generate New Card Illustrations

It is demonstrated that Magicstylegan is the state-of-the-art approach for generating Magic illustrations, and some emerging properties regarding transfer learning in GANs are highlighted, which is still a somehow under-explored field in generative learning research.

Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior

A well-designed blind face restoration network with generative facial prior that achieves superior performance to the prior art for face restoration and face super- resolution tasks and can tackle seriously degraded face images in diverse poses and expressions is proposed.

Shapes2Toon: Generating Cartoon Characters from Simple Geometric Shapes

A tool-shape2toon-that aims to automate this approach by utilizing a generative adversarial network which combines geometric primitives and generates a cartoon figure depending on the given approximation, and results show that the system can generate cartoon characters from input layout of geometric shapes.

SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines

The creation of a parameterized stylized character involves careful selection of numerous parameters, also known as the “avatar vectors” that can be interpreted by the avatar engine, which are then bridged with the avatar vectors as pairs to synthesize paired data in high-quality as many as possible.



Unsupervised Image-to-Image Translation via Pre-Trained StyleGAN2 Network

Both qualitative and quantitative evaluations were conducted to verify that the proposed I2I translation method can achieve better performance in terms of image quality, diversity and semantic similarity to the input and reference images compared to state-of-the-art works.

Analyzing and Improving the Image Quality of StyleGAN

This work redesigns the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images, and thereby redefines the state of the art in unconditional image modeling.

StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation

A unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network, which leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain.

In-Domain GAN Inversion for Real Image Editing

An in-domain GAN inversion approach, which not only faithfully reconstructs the input image but also ensures the inverted code to be semantically meaningful for editing, which achieves satisfying real image reconstruction and facilitates various image editing tasks, significantly outperforming start-of-the-arts.

Unsupervised Image-to-Image Translation Networks

This work makes a shared-latent space assumption and proposes an unsupervised image-to-image translation framework based on Coupled GANs that achieves state-of-the-art performance on benchmark datasets.

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

This work explores leveraging the power of recently introduced Contrastive Language-Image Pre-training (CLIP) models in order to develop a text-based interface for StyleGAN image manipulation that does not require such manual effort.

DualGAN: Unsupervised Dual Learning for Image-to-Image Translation

A novel dual-GAN mechanism is developed, which enables image translators to be trained from two sets of unlabeled images from two domains, and can even achieve comparable or slightly better results than conditional GAN trained on fully labeled data.

A Style-Based Generator Architecture for Generative Adversarial Networks

An alternative generator architecture for generative adversarial networks is proposed, borrowing from style transfer literature, that improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation.

Image-to-Image Translation with Conditional Adversarial Networks

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.

Freeze Discriminator: A Simple Baseline for Fine-tuning GANs

It is shown that simple fine-tuning of GANs with frozen lower layers of the discriminator performs surprisingly well, and a simple baseline, FreezeD, significantly outperforms previous techniques used in both unconditional and conditional GAns.