14 citations · 23 across the 4 of their papers we have counts for
4 papers
Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models
Paul Henderson, Melonie de Almeida, Daniela Ivanova +1
We present a latent diffusion model over 3D scenes, that can be trained using only 2D image data. To achieve this, we first design an autoencoder that maps multi-view images to 3D…
Denoising Diffusion via Image-Based Rendering
Titas Anciukevičius, Fabian Manhardt, Federico Tombari +1
Generating 3D scenes is a challenging open problem, which requires synthesizing plausible content that is fully consistent in 3D space. While recent methods such as neural radiance…
RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
Titas Anciukevičius, Zexiang Xu, Matthew Fisher +4
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 task…
Object-Centric Image Generation with Factored Depths, Locations, and Appearances
Titas Anciukevicius, Christoph H. Lampert, Paul Henderson
We present a generative model of images that explicitly reasons over the set of objects they show. Our model learns a structured latent representation that separates objects from e…