MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration

• URL: http://arxiv.org/abs/2001.01870v2
• Date: Sun, 19 Dec 2021 08:25:32 GMT
• Title: MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration
• Authors: Haodi Hou, Jing Huo, Jing Wu, Yu-Kun Lai, and Yang Gao
• Abstract summary: 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.
• Score: 53.98437317161086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given an input face photo, the goal of caricature generation is to produce stylized, exaggerated caricatures that share the same identity as the photo. It requires simultaneous style transfer and shape exaggeration with rich diversity, and meanwhile preserving the identity of the input. To address this challenging problem, we propose a novel framework called Multi-Warping GAN (MW-GAN), including a style network and a geometric network that are designed to conduct style transfer and geometric exaggeration respectively. We bridge the gap between the style and landmarks of an image with corresponding latent code spaces by a dual way design, so as to generate caricatures with arbitrary styles and geometric exaggeration, which can be specified either through random sampling of latent code or from a given caricature sample. Besides, we apply identity preserving loss to both image space and landmark space, leading to a great improvement in quality of generated caricatures. Experiments show that caricatures generated by MW-GAN have better quality than existing methods.

Related papers

• PS-StyleGAN: Illustrative Portrait Sketching using Attention-Based Style Adaptation [0.0]
  Portrait sketching involves capturing identity specific attributes of a real face with abstract lines and shades. This paper introduces textbfPortrait Sketching StyleGAN (PS-StyleGAN), a style transfer approach tailored for portrait sketch synthesis. We leverage the semantic $W+$ latent space of StyleGAN to generate portrait sketches, allowing us to make meaningful edits, like pose and expression alterations, without compromising identity.
  arXiv  Detail & Related papers  (2024-08-31T04:22:45Z)
• DemoCaricature: Democratising Caricature Generation with a Rough Sketch [80.90808879991182]
  We democratise caricature generation, empowering individuals to craft personalised caricatures with just a photo and a conceptual sketch. Our objective is to strike a delicate balance between abstraction and identity, while preserving the creativity and subjectivity inherent in a sketch.
  arXiv  Detail & Related papers  (2023-12-07T15:35:42Z)
• Portrait Diffusion: Training-free Face Stylization with Chain-of-Painting [64.43760427752532]
  Face stylization refers to the transformation of a face into a specific portrait style. Current methods require the use of example-based adaptation approaches to fine-tune pre-trained generative models. This paper proposes a training-free face stylization framework, named Portrait Diffusion.
  arXiv  Detail & Related papers  (2023-12-03T06:48:35Z)
• Face Cartoonisation For Various Poses Using StyleGAN [0.7673339435080445]
  This paper presents an innovative approach to achieve face cartoonisation while preserving the original identity and accommodating various poses. We achieve this by introducing an encoder that captures both pose and identity information from images and generates a corresponding embedding within the StyleGAN latent space. We show by extensive experimentation how our encoder adapts the StyleGAN output to better preserve identity when the objective is cartoonisation.
  arXiv  Detail & Related papers  (2023-09-26T13:10:25Z)
• Cross-Domain Style Mixing for Face Cartoonization [6.174413879403037]
  We propose a novel method called Cross-domain Style mixing, which combines two latent codes from two different domains. Our method effectively stylizes faces into multiple cartoon characters at various face abstraction levels using only a single generator.
  arXiv  Detail & Related papers  (2022-05-25T02:39:10Z)
• Unsupervised Contrastive Photo-to-Caricature Translation based on Auto-distortion [49.93278173824292]
  Photo-to-caricature aims to synthesize the caricature as a rendered image exaggerating the features through sketching, pencil strokes, or other artistic drawings. Style rendering and geometry deformation are the most important aspects in photo-to-caricature translation task. We propose an unsupervised contrastive photo-to-caricature translation architecture.
  arXiv  Detail & Related papers  (2020-11-10T08:14:36Z)
• CariMe: Unpaired Caricature Generation with Multiple Exaggerations [22.342630945133312]
  Caricature generation aims to translate real photos into caricatures with artistic styles and shape exaggerations. Previous caricature generation methods are obsessed with predicting definite image warping from a given photo. We propose a Multi-exaggeration Warper network to learn the distribution-level mapping from photo to facial exaggerations.
  arXiv  Detail & Related papers  (2020-10-01T08:14:32Z)
• DeepFacePencil: Creating Face Images from Freehand Sketches [77.00929179469559]
  Existing image-to-image translation methods require a large-scale dataset of paired sketches and images for supervision. We propose DeepFacePencil, an effective tool that is able to generate photo-realistic face images from hand-drawn sketches.
  arXiv  Detail & Related papers  (2020-08-31T03:35:21Z)
• Modeling Caricature Expressions by 3D Blendshape and Dynamic Texture [58.78290175562601]
  This paper presents a solution to the problem of deforming an artist-drawn caricature according to a given normal face expression. The key of our solution is a novel method to model caricature expression, which extends traditional 3DMM representation to caricature domain. The experiments demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2020-08-13T06:31:01Z)

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.