LatentSwap3D: Semantic Edits on 3D Image GANs
- URL: http://arxiv.org/abs/2212.01381v2
- Date: Mon, 4 Sep 2023 19:12:46 GMT
- Title: LatentSwap3D: Semantic Edits on 3D Image GANs
- Authors: Enis Simsar and Alessio Tonioni and Evin P{\i}nar \"Ornek and Federico
Tombari
- Abstract summary: 3D GANs can generate latent codes for entire 3D volumes rather than only 2D images.
LatentSwap3D is a semantic edit approach based on latent space discovery.
We show results on seven 3D GANs and on five datasets.
- Score: 48.1271011449138
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 3D GANs have the ability to generate latent codes for entire 3D volumes
rather than only 2D images. These models offer desirable features like
high-quality geometry and multi-view consistency, but, unlike their 2D
counterparts, complex semantic image editing tasks for 3D GANs have only been
partially explored. To address this problem, we propose LatentSwap3D, a
semantic edit approach based on latent space discovery that can be used with
any off-the-shelf 3D or 2D GAN model and on any dataset. LatentSwap3D relies on
identifying the latent code dimensions corresponding to specific attributes by
feature ranking using a random forest classifier. It then performs the edit by
swapping the selected dimensions of the image being edited with the ones from
an automatically selected reference image. Compared to other latent space
control-based edit methods, which were mainly designed for 2D GANs, our method
on 3D GANs provides remarkably consistent semantic edits in a disentangled
manner and outperforms others both qualitatively and quantitatively. We show
results on seven 3D GANs (pi-GAN, GIRAFFE, StyleSDF, MVCGAN, EG3D, StyleNeRF,
and VolumeGAN) and on five datasets (FFHQ, AFHQ, Cats, MetFaces, and CompCars).
Related papers
- 3DStyle-Diffusion: Pursuing Fine-grained Text-driven 3D Stylization with
2D Diffusion Models [102.75875255071246]
3D content creation via text-driven stylization has played a fundamental challenge to multimedia and graphics community.
We propose a new 3DStyle-Diffusion model that triggers fine-grained stylization of 3D meshes with additional controllable appearance and geometric guidance from 2D Diffusion models.
arXiv Detail & Related papers (2023-11-09T15:51:27Z) - HyperStyle3D: Text-Guided 3D Portrait Stylization via Hypernetworks [101.36230756743106]
This paper is inspired by the success of 3D-aware GANs that bridge 2D and 3D domains with 3D fields as the intermediate representation for rendering 2D images.
We propose a novel method, dubbed HyperStyle3D, based on 3D-aware GANs for 3D portrait stylization.
arXiv Detail & Related papers (2023-04-19T07:22:05Z) - CC3D: Layout-Conditioned Generation of Compositional 3D Scenes [49.281006972028194]
We introduce CC3D, a conditional generative model that synthesizes complex 3D scenes conditioned on 2D semantic scene layouts.
Our evaluations on synthetic 3D-FRONT and real-world KITTI-360 datasets demonstrate that our model generates scenes of improved visual and geometric quality.
arXiv Detail & Related papers (2023-03-21T17:59:02Z) - 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) - SSR-2D: Semantic 3D Scene Reconstruction from 2D Images [54.46126685716471]
In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any 3D annotations.
The key idea of our approach is to design a trainable model that employs both incomplete 3D reconstructions and their corresponding source RGB-D images.
Our method achieves the state-of-the-art performance of semantic scene completion on two large-scale benchmark datasets MatterPort3D and ScanNet.
arXiv Detail & Related papers (2023-02-07T17:47:52Z) - 3D GAN Inversion with Pose Optimization [26.140281977885376]
We introduce a generalizable 3D GAN inversion method that infers camera viewpoint and latent code simultaneously to enable multi-view consistent semantic image editing.
We conduct extensive experiments on image reconstruction and editing both quantitatively and qualitatively, and further compare our results with 2D GAN-based editing.
arXiv Detail & Related papers (2022-10-13T19:06:58Z) - FENeRF: Face Editing in Neural Radiance Fields [34.332520597067074]
We propose FENeRF, a 3D-aware generator that can produce view-consistent and locally-editable portrait images.
Our method uses two decoupled latent codes to generate corresponding facial semantics and texture in a spatial aligned 3D volume with shared geometry.
Our experiments demonstrate that FENeRF outperforms state-of-the-art methods in various face editing tasks.
arXiv Detail & Related papers (2021-11-30T15:23:08Z) - 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) - Convolutional Generation of Textured 3D Meshes [34.20939983046376]
We propose a framework that can generate triangle meshes and associated high-resolution texture maps, using only 2D supervision from single-view natural images.
A key contribution of our work is the encoding of the mesh and texture as 2D representations, which are semantically aligned and can be easily modeled by a 2D convolutional GAN.
We demonstrate the efficacy of our method on Pascal3D+ Cars and CUB, both in an unconditional setting and in settings where the model is conditioned on class labels, attributes, and text.
arXiv Detail & Related papers (2020-06-13T15:23:29Z)
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.