42 citations · 56 across the 8 of their papers we have counts for
10 papers
Disentangled 3D Scene Generation with Layout Learning
Dave Epstein, Ben Poole, Ben Mildenhall +2
We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretr…
Online Detection of AI-Generated Images
David C. Epstein, Ishan Jain, Oliver Wang +1
With advancements in AI-generated images coming on a continuous basis, it is increasingly difficult to distinguish traditionally-sourced images (e.g., photos, artwork) from AI-gene…
Diffusion Self-Guidance for Controllable Image Generation
Dave Epstein, Allan Jabri, Ben Poole +2
Large-scale generative models are capable of producing high-quality images from detailed text descriptions. However, many aspects of an image are difficult or impossible to convey…
BlobGAN: Spatially Disentangled Scene Representations
Dave Epstein, Taesung Park, Richard Zhang +2
We propose an unsupervised, mid-level representation for a generative model of scenes. The representation is mid-level in that it is neither per-pixel nor per-image; rather, scenes…
Learning Temporal Dynamics from Cycles in Narrated Video
Dave Epstein, Jiajun Wu, Cordelia Schmid +1
Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem us…
Globetrotter: Connecting Languages by Connecting Images
Dídac Surís, Dave Epstein, Carl Vondrick
Machine translation between many languages at once is highly challenging, since training with ground truth requires supervision between all language pairs, which is difficult to ob…