StyleRig: Rigging StyleGAN for 3D Control over Portrait Images

• URL: http://arxiv.org/abs/2004.00121v2
• Date: Sat, 13 Jun 2020 09:40:33 GMT
• Title: StyleRig: Rigging StyleGAN for 3D Control over Portrait Images
• Authors: Ayush Tewari, Mohamed Elgharib, Gaurav Bharaj, Florian Bernard, Hans-Peter Seidel, Patrick P\'erez, Michael Zollh\"ofer, Christian Theobalt
• Abstract summary: StyleGAN generates portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background) StyleGAN lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination. We present the first method to provide a face rig-like control over a pretrained and fixed StyleGAN via a 3DMM.
• Score: 81.43265493604302
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination. Three-dimensional morphable face models (3DMMs) on the other hand offer control over the semantic parameters, but lack photorealism when rendered and only model the face interior, not other parts of a portrait image (hair, mouth interior, background). We present the first method to provide a face rig-like control over a pretrained and fixed StyleGAN via a 3DMM. A new rigging network, RigNet is trained between the 3DMM's semantic parameters and StyleGAN's input. The network is trained in a self-supervised manner, without the need for manual annotations. At test time, our method generates portrait images with the photorealism of StyleGAN and provides explicit control over the 3D semantic parameters of the face.

Related papers

• FaceGPT: Self-supervised Learning to Chat about 3D Human Faces [69.4651241319356]
  We introduce FaceGPT, a self-supervised learning framework for Large Vision-Language Models (VLMs) to reason about 3D human faces from images and text. FaceGPT overcomes this limitation by embedding the parameters of a 3D morphable face model (3DMM) into the token space of a VLM. We show that FaceGPT achieves high-quality 3D face reconstructions and retains the ability for general-purpose visual instruction following.
  arXiv  Detail & Related papers  (2024-06-11T11:13:29Z)
• AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collections [78.81539337399391]
  We present an animatable 3D-aware GAN that generates portrait images with controllable facial expression, head pose, and shoulder movements. It is a generative model trained on unstructured 2D image collections without using 3D or video data. A dual-camera rendering and adversarial learning scheme is proposed to improve the quality of the generated faces.
  arXiv  Detail & Related papers  (2023-09-05T12:44:57Z)
• Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization [91.52882218901627]
  We propose a novel method for constructing implicit 3D morphable face models that are both generalizable and intuitive for editing. Our method improves upon photo-realism, geometry, and expression accuracy compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-04T17:58:40Z)
• Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars [36.4402388864691]
  3D-aware generative adversarial networks (GANs) synthesize high-fidelity and multi-view-consistent facial images using only collections of single-view 2D imagery. Recent efforts incorporate 3D Morphable Face Model (3DMM) to describe deformation in generative radiance fields either explicitly or implicitly. We propose a novel 3D GAN framework for unsupervised learning of generative, high-quality and 3D-consistent facial avatars from unstructured 2D images.
  arXiv  Detail & Related papers  (2022-11-21T06:40:46Z)
• Controllable Face Manipulation and UV Map Generation by Self-supervised Learning [20.10160338724354]
  Recent methods achieve explicit control over 2D images by combining 2D generative model and 3DMM. Due to the lack of realism and clarity in texture reconstruction by 3DMM, there is a domain gap between the synthetic image and the rendered image of 3DMM. In this study, we propose to explicitly edit the latent space of the pretrained StyleGAN by controlling the parameters of the 3DMM.
  arXiv  Detail & Related papers  (2022-09-24T16:49:25Z)
• MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation [69.35523133292389]
  We propose a framework that a priori models physical attributes of the face explicitly, thus providing disentanglement by design. Our method, MOST-GAN, integrates the expressive power and photorealism of style-based GANs with the physical disentanglement and flexibility of nonlinear 3D morphable models. It achieves photorealistic manipulation of portrait images with fully disentangled 3D control over their physical attributes, enabling extreme manipulation of lighting, facial expression, and pose variations up to full profile view.
  arXiv  Detail & Related papers  (2021-11-01T15:53:36Z)
• Cross-Domain and Disentangled Face Manipulation with 3D Guidance [33.43993665841577]
  We propose the first method to manipulate faces in arbitrary domains using human 3DMM. This is achieved through two major steps: 1) disentangled mapping from 3DMM parameters to the latent space embedding of a pre-trained StyleGAN2. Experiments and comparisons demonstrate the superiority of our high-quality semantic manipulation method on a variety of face domains.
  arXiv  Detail & Related papers  (2021-04-22T17:59:50Z)
• Lifting 2D StyleGAN for 3D-Aware Face Generation [52.8152883980813]
  We propose a framework, called LiftedGAN, that disentangles and lifts a pre-trained StyleGAN2 for 3D-aware face generation. Our model is "3D-aware" in the sense that it is able to (1) disentangle the latent space of StyleGAN2 into texture, shape, viewpoint, lighting and (2) generate 3D components for synthetic images.
  arXiv  Detail & Related papers  (2020-11-26T05:02:09Z)
• GIF: Generative Interpretable Faces [16.573491296543196]
  3D face modeling methods provide parametric control but generate unrealistic images. Recent methods gain partial control, either by attempting to disentangle different factors in an unsupervised manner, or by adding control post hoc to a pre-trained model. We condition our generative model on pre-defined control parameters to encourage disentanglement in the generation process.
  arXiv  Detail & Related papers  (2020-08-31T23:40:26Z)

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.