3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis

• URL: http://arxiv.org/abs/2401.03764v1
• Date: Mon, 8 Jan 2024 09:41:07 GMT
• Title: 3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis
• Authors: Ruiqi Liu, Peng Zheng, Ye Wang, Rui Ma
• Abstract summary: Existing 3D-aware portrait synthesis methods can generate impressive high-quality images while preserving strong 3D consistency. We propose 3D-SSGAN, a novel framework for 3D-aware compositional portrait image synthesis.
• Score: 11.457566989721078
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing 3D-aware portrait synthesis methods can generate impressive high-quality images while preserving strong 3D consistency. However, most of them cannot support the fine-grained part-level control over synthesized images. Conversely, some GAN-based 2D portrait synthesis methods can achieve clear disentanglement of facial regions, but they cannot preserve view consistency due to a lack of 3D modeling abilities. To address these issues, we propose 3D-SSGAN, a novel framework for 3D-aware compositional portrait image synthesis. First, a simple yet effective depth-guided 2D-to-3D lifting module maps the generated 2D part features and semantics to 3D. Then, a volume renderer with a novel 3D-aware semantic mask renderer is utilized to produce the composed face features and corresponding masks. The whole framework is trained end-to-end by discriminating between real and synthesized 2D images and their semantic masks. Quantitative and qualitative evaluations demonstrate the superiority of 3D-SSGAN in controllable part-level synthesis while preserving 3D view consistency.

Related papers

• 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)
• Mimic3D: Thriving 3D-Aware GANs via 3D-to-2D Imitation [29.959223778769513]
  We propose a novel learning strategy, namely 3D-to-2D imitation, which enables a 3D-aware GAN to generate high-quality images. We also introduce 3D-aware convolutions into the generator for better 3D representation learning. With the above strategies, our method reaches FID scores of 5.4 and 4.3 on FFHQ and AFHQ-v2 Cats, respectively, at 512x512 resolution.
  arXiv  Detail & Related papers  (2023-03-16T02:18:41Z)
• CGOF++: Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields [52.14985242487535]
  We propose a new conditional 3D face synthesis framework, which enables 3D controllability over generated face images. At its core is a conditional Generative Occupancy Field (cGOF++) that effectively enforces the shape of the generated face to conform to a given 3D Morphable Model (3DMM) mesh. Experiments validate the effectiveness of the proposed method and show more precise 3D controllability than state-of-the-art 2D-based controllable face synthesis methods.
  arXiv  Detail & Related papers  (2022-11-23T19:02:50Z)
• 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)
• Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields [40.2714783162419]
  We propose a new conditional 3D face synthesis framework, which enables 3D controllability over generated face images. At its core is a conditional Generative Occupancy Field (cGOF) that effectively enforces the shape of the generated face to commit to a given 3D Morphable Model (3DMM) mesh. Experiments validate the effectiveness of the proposed method, which is able to generate high-fidelity face images.
  arXiv  Detail & Related papers  (2022-06-16T17:58:42Z)
• Realistic Image Synthesis with Configurable 3D Scene Layouts [59.872657806747576]
  We propose a novel approach to realistic-looking image synthesis based on a 3D scene layout. Our approach takes a 3D scene with semantic class labels as input and trains a 3D scene painting network. With the trained painting network, realistic-looking images for the input 3D scene can be rendered and manipulated.
  arXiv  Detail & Related papers  (2021-08-23T09:44:56Z)
• STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar? [20.58364192180389]
  We propose a novel generative adversarial nets-based framework (STS-GAN) to extend the given 2D exemplar to arbitrary 3D solid textures. In STS-GAN, multi-scale 2D texture discriminators evaluate the similarity between the given 2D exemplar and slices from the generated 3D texture, promoting the 3D texture generator synthesizing realistic solid textures.
  arXiv  Detail & Related papers  (2021-02-08T02:51:34Z)
• 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)
• Towards Realistic 3D Embedding via View Alignment [53.89445873577063]
  This paper presents an innovative View Alignment GAN (VA-GAN) that composes new images by embedding 3D models into 2D background images realistically and automatically. VA-GAN consists of a texture generator and a differential discriminator that are inter-connected and end-to-end trainable.
  arXiv  Detail & Related papers  (2020-07-14T14:45:00Z)

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.