Projects per year
Abstract / Description of output
Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support tasks required for 3D understanding, such as view-consistent 3D generation or single-view object reconstruction. In this paper, we present RenderDiffusion, the first diffusion model for 3D generation and inference, trained using only monocular 2D supervision. Central to our method is a novel image denoising architecture that generates and renders an intermediate three-dimensional representation of a scene in each denoising step. This enforces a strong inductive structure within the diffusion process, providing a 3D consistent representation while only requiring 2D supervision. The resulting 3D representation can be rendered from any view. We evaluate RenderDiffusion on FFHQ, AFHQ, ShapeNet and CLEVR datasets, showing competitive performance for generation of 3D scenes and inference of 3D scenes from 2D images. Additionally, our diffusion-based approach allows us to use 2D inpainting to edit 3D scenes.
Original language | English |
---|---|
Title of host publication | Computer Vision and Pattern Recognition 2023 |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 12608-12618 |
Number of pages | 11 |
ISBN (Electronic) | 979-8-3503-0129-8 |
ISBN (Print) | 979-8-3503-0130-4 |
DOIs | |
Publication status | Published - 22 Aug 2023 |
Event | The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 - Vancouver Convention Center, Vancouver, Canada Duration: 18 Jun 2023 → 22 Jun 2023 https://cvpr2023.thecvf.com/ |
Publication series
Name | |
---|---|
ISSN (Print) | 1063-6919 |
ISSN (Electronic) | 2575-7075 |
Conference
Conference | The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 |
---|---|
Abbreviated title | CVPR 2023 |
Country/Territory | Canada |
City | Vancouver |
Period | 18/06/23 → 22/06/23 |
Internet address |
Keywords / Materials (for Non-textual outputs)
- cs.CV
- cs.LG
Fingerprint
Dive into the research topics of 'RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation'. Together they form a unique fingerprint.Projects
- 1 Active
-
Visual AI: An Open World Interpretable Visual Transformer
Engineering and Physical Sciences Research Council
1/12/20 → 30/11/26
Project: Research