808 citations · 2.4k across the 21 of their papers we have counts for
15 papers · 1 filter
HoloDiffusion: Training a 3D Diffusion Model using 2D Images
Animesh Karnewar, Andrea Vedaldi, David Novotny +1
Diffusion models have emerged as the best approach for generative modeling of 2D images. Part of their success is due to the possibility of training them on millions if not billion…
: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction
Luke Melas-Kyriazi, Christian Rupprecht, Andrea Vedaldi
Reconstructing the 3D shape of an object from a single RGB image is a long-standing and highly challenging problem in computer vision. In this paper, we propose a novel method for…
RealFusion: 360° Reconstruction of Any Object from a Single Image
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina +1
We consider the problem of reconstructing a full 360° photographic model of an object from a single image of it. We do so by fitting a neural radiance field to the image, but find…
Text-To-4D Dynamic Scene Generation
Uriel Singer, Shelly Sheynin, Adam Polyak +8
We present MAV3D (Make-A-Video3D), a method for generating three-dimensional dynamic scenes from text descriptions. Our approach uses a 4D dynamic Neural Radiance Field (NeRF), whi…
Audio-Visual Synchronisation in the wild
Honglie Chen, Weidi Xie, Triantafyllos Afouras +3
In this paper, we consider the problem of audio-visual synchronisation applied to videos `in-the-wild' (ie of general classes beyond speech). As a new task, we identify and curate…
ResearchDoom and CocoDoom: Learning Computer Vision with Games
A. Mahendran, H. Bilen, J. F. Henriques +1
In this short note we introduce ResearchDoom, an implementation of the Doom first-person shooter that can extract detailed metadata from the game. We also introduce the CocoDoom da…