GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds

• URL: http://arxiv.org/abs/2206.07255v2
• Date: Wed, 11 Oct 2023 08:41:34 GMT
• Title: GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds
• Authors: Jianfeng Xiang, Jiaolong Yang, Yu Deng, Xin Tong
• Abstract summary: 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.
• Score: 28.660893916203747
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent works have shown that 3D-aware GANs trained on unstructured single image collections can generate multiview images of novel instances. The key underpinnings to achieve this are a 3D radiance field generator and a volume rendering process. However, existing methods either cannot generate high-resolution images (e.g., up to 256X256) due to the high computation cost of neural volume rendering, or rely on 2D CNNs for image-space upsampling which jeopardizes the 3D consistency across different views. 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. We avoid the otherwise prohibitively-expensive computation cost by applying 2D convolutions on a set of 2D radiance manifolds defined in the recent generative radiance manifold (GRAM) approach, and apply dedicated loss functions for effective GAN training at high resolution. Experiments on FFHQ and AFHQv2 datasets show that our method can produce high-quality 3D-consistent results that significantly outperform existing methods. It makes a significant step towards closing the gap between traditional 2D image generation and 3D-consistent free-view generation.

Related papers

• IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation [96.32684334038278]
  In this paper, we explore the design space of text-to-3D models. We significantly improve multi-view generation by considering video instead of image generators. Our new method, IM-3D, reduces the number of evaluations of the 2D generator network 10-100x.
  arXiv  Detail & Related papers  (2024-02-13T18:59:51Z)
• 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)
• HoloFusion: Towards Photo-realistic 3D Generative Modeling [77.03830223281787]
  Diffusion-based image generators can now produce high-quality and diverse samples, but their success has yet to fully translate to 3D generation. We present HoloFusion, a method that combines the best of these approaches to produce high-fidelity, plausible, and diverse 3D samples.
  arXiv  Detail & Related papers  (2023-08-28T01:19:33Z)
• 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)
• GVP: Generative Volumetric Primitives [76.95231302205235]
  We present Generative Volumetric Primitives (GVP), the first pure 3D generative model that can sample and render 512-resolution images in real-time. GVP jointly models a number of primitives and their spatial information, both of which can be efficiently generated via a 2D convolutional network. Experiments on several datasets demonstrate superior efficiency and 3D consistency of GVP over the state-of-the-art.
  arXiv  Detail & Related papers  (2023-03-31T16:50:23Z)
• 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)
• 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: Generative Radiance Manifolds for 3D-Aware Image Generation [25.20217335614512]
  3D-aware image generative modeling aims to generate 3D-consistent images with explicitly controllable camera poses. Recent works have shown promising results by training neural radiance field (NeRF) generators on unstructured 2D images.
  arXiv  Detail & Related papers  (2021-12-16T13:25:49Z)

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.