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 as the first diffusion model for 3D generation and inference that can be trained using only monocular 2D supervision. At the heart of 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 into the diffusion process that gives us a 3D consistent representation while only requiring 2D supervision. The resulting 3D representation can be rendered from any viewpoint. We evaluate RenderDiffusion on ShapeNet and Clevr datasets and show 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. We believe that our work promises to enable full 3D generation at scale when trained on massive image collections, thus circumventing the need to have large-scale 3D model collections for supervision.

本文提出了RenderDiffusion，这是第一个用于3D生成和推断的扩散模型，使用仅有的单眼2D监督进行训练，并采用新颖的图像去噪架构进行中间的三维表示，以提供强烈归纳结构，同时仅需要2D监督。我们在FFHQ、AFHQ、ShapeNet和CLEVR数据集上评估了RenderDiffusion，展示了生成3D场景和从2D图像中推理3D场景的竞争性表现。此外，我们的扩散型方法还使我们能够使用2D修复来编辑3D场景。

RenderDiffusion：用于3D重建、修补与生成的图像扩散