Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion
- URL: http://arxiv.org/abs/2212.07409v2
- Date: Thu, 15 Dec 2022 12:22:08 GMT
- Title: Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion
- Authors: Yushi Lan, Xuyi Meng, Shuai Yang, Chen Change Loy, Bo Dai
- Abstract summary: StyleGAN has achieved great progress in 2D face reconstruction and semantic editing via image inversion and latent editing.
A corresponding generic 3D GAN inversion framework is still missing, limiting the applications of 3D face reconstruction and semantic editing.
We study the challenging problem of 3D GAN inversion where a latent code is predicted given a single face image to faithfully recover its 3D shapes and detailed textures.
- Score: 115.82306502822412
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: StyleGAN has achieved great progress in 2D face reconstruction and semantic
editing via image inversion and latent editing. While studies over extending 2D
StyleGAN to 3D faces have emerged, a corresponding generic 3D GAN inversion
framework is still missing, limiting the applications of 3D face reconstruction
and semantic editing. In this paper, we study the challenging problem of 3D GAN
inversion where a latent code is predicted given a single face image to
faithfully recover its 3D shapes and detailed textures. The problem is
ill-posed: innumerable compositions of shape and texture could be rendered to
the current image. Furthermore, with the limited capacity of a global latent
code, 2D inversion methods cannot preserve faithful shape and texture at the
same time when applied to 3D models. To solve this problem, we devise an
effective self-training scheme to constrain the learning of inversion. The
learning is done efficiently without any real-world 2D-3D training pairs but
proxy samples generated from a 3D GAN. In addition, apart from a global latent
code that captures the coarse shape and texture information, we augment the
generation network with a local branch, where pixel-aligned features are added
to faithfully reconstruct face details. We further consider a new pipeline to
perform 3D view-consistent editing. Extensive experiments show that our method
outperforms state-of-the-art inversion methods in both shape and texture
reconstruction quality. Code and data will be released.
Related papers
- What You See is What You GAN: Rendering Every Pixel for High-Fidelity
Geometry in 3D GANs [82.3936309001633]
3D-aware Generative Adversarial Networks (GANs) have shown remarkable progress in learning to generate multi-view-consistent images and 3D geometries.
Yet, the significant memory and computational costs of dense sampling in volume rendering have forced 3D GANs to adopt patch-based training or employ low-resolution rendering with post-processing 2D super resolution.
We propose techniques to scale neural volume rendering to the much higher resolution of native 2D images, thereby resolving fine-grained 3D geometry with unprecedented detail.
arXiv Detail & Related papers (2024-01-04T18:50:38Z) - Designing a 3D-Aware StyleNeRF Encoder for Face Editing [15.303426697795143]
We propose a 3D-aware encoder for GAN inversion and face editing based on the powerful StyleNeRF model.
Our proposed 3Da encoder combines a parametric 3D face model with a learnable detail representation model to generate geometry, texture and view direction codes.
arXiv Detail & Related papers (2023-02-19T03:32:28Z) - 3D GAN Inversion with Facial Symmetry Prior [42.22071135018402]
It is natural to associate 3D GANs with GAN inversion methods to project a real image into the generator's latent space.
We propose a novel method to promote 3D GAN inversion by introducing facial symmetry prior.
arXiv Detail & Related papers (2022-11-30T11:57:45Z) - High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization [51.878078860524795]
We present a high-fidelity 3D generative adversarial network (GAN) inversion framework that can synthesize photo-realistic novel views.
Our approach enables high-fidelity 3D rendering from a single image, which is promising for various applications of AI-generated 3D content.
arXiv Detail & Related papers (2022-11-28T18:59:52Z) - Pruning-based Topology Refinement of 3D Mesh using a 2D Alpha Mask [6.103988053817792]
We present a method to refine the topology of any 3D mesh through a face-pruning strategy.
Our solution leverages a differentiable that renders each face as a 2D soft map.
Because our module is agnostic to the network that produces the 3D mesh, it can be easily plugged into any self-supervised image-based 3D reconstruction pipeline.
arXiv Detail & Related papers (2022-10-17T14:51:38Z) - XDGAN: Multi-Modal 3D Shape Generation in 2D Space [60.46777591995821]
We propose a novel method to convert 3D shapes into compact 1-channel geometry images and leverage StyleGAN3 and image-to-image translation networks to generate 3D objects in 2D space.
The generated geometry images are quick to convert to 3D meshes, enabling real-time 3D object synthesis, visualization and interactive editing.
We show both quantitatively and qualitatively that our method is highly effective at various tasks such as 3D shape generation, single view reconstruction and shape manipulation, while being significantly faster and more flexible compared to recent 3D generative models.
arXiv Detail & Related papers (2022-10-06T15:54:01Z) - Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape [77.95154911528365]
3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori.
Previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry.
This paper proposes a complete solution to capture the personalized shape so that the reconstructed shape looks identical to the corresponding person.
arXiv Detail & Related papers (2022-04-09T03:46:18Z) - An Effective Loss Function for Generating 3D Models from Single 2D Image
without Rendering [0.0]
Differentiable rendering is a very successful technique that applies to a Single-View 3D Reconstruction.
Currents use losses based on pixels between a rendered image of some 3D reconstructed object and ground-truth images from given matched viewpoints to optimise parameters of the 3D shape.
We propose a novel effective loss function that evaluates how well the projections of reconstructed 3D point clouds cover the ground truth object's silhouette.
arXiv Detail & Related papers (2021-03-05T00:02:18Z) - Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D
Image GANs [156.1209884183522]
State-of-the-art 2D generative models like GANs show unprecedented quality in modeling the natural image manifold.
We present the first attempt to directly mine 3D geometric cues from an off-the-shelf 2D GAN that is trained on RGB images only.
arXiv Detail & Related papers (2020-11-02T09:38:43Z)
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.