2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)· 2022
StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation
- 235citations
- 2022year
Short summary
StyleSDF generates high-resolution, 3D-consistent images and detailed 3D shapes from single-view RGB data by merging a Signed Distance Function (SDF) 3D representation with a StyleGAN2 image generator.
AI-generated from the title and abstract; the full text is not read.
Key points
- Generates high-resolution (1024x1024), 3D-consistent images and detailed 3D shapes from single-view RGB data.
- Merges a Signed Distance Function (SDF) based 3D representation with a StyleGAN2-based image generator.
- The 3D implicit network renders low-resolution feature maps for the style-based generator.
- Achieves higher visual and geometric quality compared to existing state-of-the-art methods.
AI-generated from the title and abstract; the full text is not read.
Abstract
We introduce a high resolution, 3D-consistent image and shape generation technique which we call StyleSDF. Our method is trained on single-view RGB data only, and stands on the shoulders of StyleGAN2 for image generation, while solving two main challenges in 3D-aware GANs: 1) high-resolution, view-consistent generation of the RGB images, and 2) detailed 3D shape. We achieve this by merging a SDF-based 3D representation with a style-based 2D generator. Our 3D implicit network renders low-resolution feature maps, from which the style-based network generates view-consistent, 1024×1024 images. Notably, our SDF-based 3D modeling defines detailed 3D surfaces, leading to consistent volume rendering. Our method shows higher quality results compared to state of the art in terms of visual and geometric quality.
The authors' abstract, as published at the source. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Graphics and Computer-Aided Design
Computer Graphics and Computer-Aided DesignComputer Science