Mimic3D: Thriving 3D-Aware GANs via 3D-to-2D Imitation

• URL: http://arxiv.org/abs/2303.09036v2
• Date: Mon, 7 Aug 2023 08:10:55 GMT
• Title: Mimic3D: Thriving 3D-Aware GANs via 3D-to-2D Imitation
• Authors: Xingyu Chen, Yu Deng, Baoyuan Wang
• Abstract summary: 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.
• Score: 29.959223778769513
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Generating images with both photorealism and multiview 3D consistency is crucial for 3D-aware GANs, yet existing methods struggle to achieve them simultaneously. Improving the photorealism via CNN-based 2D super-resolution can break the strict 3D consistency, while keeping the 3D consistency by learning high-resolution 3D representations for direct rendering often compromises image quality. In this paper, we propose a novel learning strategy, namely 3D-to-2D imitation, which enables a 3D-aware GAN to generate high-quality images while maintaining their strict 3D consistency, by letting the images synthesized by the generator's 3D rendering branch to mimic those generated by its 2D super-resolution branch. We also introduce 3D-aware convolutions into the generator for better 3D representation learning, which further improves the image generation quality. 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, largely outperforming existing 3D-aware GANs using direct 3D rendering and coming very close to the previous state-of-the-art method that leverages 2D super-resolution. Project website: https://seanchenxy.github.io/Mimic3DWeb.

Related papers

• Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models [112.2625368640425]
  High-resolution Image-to-3D model (Hi3D) is a new video diffusion based paradigm that redefines a single image to multi-view images as 3D-aware sequential image generation. Hi3D first empowers the pre-trained video diffusion model with 3D-aware prior, yielding multi-view images with low-resolution texture details.
  arXiv  Detail & Related papers  (2024-09-11T17:58:57Z)
• ScalingGaussian: Enhancing 3D Content Creation with Generative Gaussian Splatting [30.99112626706754]
  The creation of high-quality 3D assets is paramount for applications in digital heritage, entertainment, and robotics. Traditionally, this process necessitates skilled professionals and specialized software for modeling. We introduce a novel 3D content creation framework, which generates 3D textures efficiently.
  arXiv  Detail & Related papers  (2024-07-26T18:26:01Z)
• 3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis [11.457566989721078]
  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.
  arXiv  Detail & Related papers  (2024-01-08T09:41:07Z)
• 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)
• Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors [104.79392615848109]
  We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes from a single unposed image. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture.
  arXiv  Detail & Related papers  (2023-06-30T17:59:08Z)
• 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)
• 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)
• GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds [28.660893916203747]
  This paper proposes a novel 3D-aware GAN that can generate high resolution images (up to 1024X1024) while keeping strict 3D consistency as in volume rendering. Our motivation is to achieve super-resolution directly in the 3D space to preserve 3D consistency. Experiments on FFHQ and AFHQv2 datasets show that our method can produce high-quality 3D-consistent results.
  arXiv  Detail & Related papers  (2022-06-15T02:35:51Z)
• 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)

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.