activity
20182022
most citedImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis

52 citations · 74 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

12 papers · 1 filter

cs.CV2022

Towards Unified Keyframe Propagation Models

Patrick Esser, Peter Michael, Soumyadip Sengupta

Many video editing tasks such as rotoscoping or object removal require the propagation of context across frames. While transformers and other attention-based approaches that aggreg…

cs.CV202152 cited

ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis

Patrick Esser, Robin Rombach, Andreas Blattmann +1

Autoregressive models and their sequential factorization of the data likelihood have recently demonstrated great potential for image representation and synthesis. Nevertheless, the…

cs.CV2021

Geometry-Free View Synthesis: Transformers and no 3D Priors

Robin Rombach, Patrick Esser, Björn Ommer

Is a geometric model required to synthesize novel views from a single image? Being bound to local convolutions, CNNs need explicit 3D biases to model geometric transformations. In…

cs.CV202115 cited

Shape or Texture: Understanding Discriminative Features in CNNs

Md Amirul Islam, Matthew Kowal, Patrick Esser +4

Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs act…

cs.CV20207 cited

A Note on Data Biases in Generative Models

Patrick Esser, Robin Rombach, Björn Ommer

It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter a…

cs.CV2020

Taming Transformers for High-Resolution Image Synthesis

Patrick Esser, Robin Rombach, Björn Ommer

Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain n…