1 code implementation • 27 Sep 2021 • Nikolay Jetchev
If a picture is worth thousand words, a moving 3d shape must be worth a million.
1 code implementation • 8 Jul 2021 • Nikolay Jetchev, Gökhan Yildirim, Christian Bracher, Roland Vollgraf
Attention is a general reasoning mechanism than can flexibly deal with image information, but its memory requirements had made it so far impractical for high resolution image generation.
no code implementations • 16 Oct 2019 • Nikolay Jetchev, Urs Bergmann, Gökhan Yildirim
Cutting and pasting image segments feels intuitive: the choice of source templates gives artists flexibility in recombining existing source material.
no code implementations • 23 Aug 2019 • Gökhan Yildirim, Nikolay Jetchev, Roland Vollgraf, Urs Bergmann
Visualizing an outfit is an essential part of shopping for clothes.
Conditional Image Generation Vocal Bursts Intensity Prediction
no code implementations • ICLR 2019 • Gökhan Yildirim, Nikolay Jetchev, Urs Bergmann
In addition, we illustrate that simple guidance functions we use in UD-GAN-G allow us to directly capture the desired variations in the data.
5 code implementations • 22 Nov 2018 • Nikolay Jetchev, Urs Bergmann, Gokhan Yildirim
Parametric generative deep models are state-of-the-art for photo and non-photo realistic image stylization.
1 code implementation • ICML 2018 • Calvin Seward, Thomas Unterthiner, Urs Bergmann, Nikolay Jetchev, Sepp Hochreiter
To formally describe an optimal update direction, we introduce a theoretical framework which allows the derivation of requirements on both the divergence and corresponding method for determining an update direction, with these requirements guaranteeing unbiased mini-batch updates in the direction of steepest descent.
Ranked #2 on Image Generation on LSUN Bedroom 64 x 64
no code implementations • 1 Dec 2017 • Nikolay Jetchev, Urs Bergmann, Calvin Seward
This paper presents a novel framework for generating texture mosaics with convolutional neural networks.
2 code implementations • 14 Sep 2017 • Nikolay Jetchev, Urs Bergmann
We present a novel method to solve image analogy problems : it allows to learn the relation between paired images present in training data, and then generalize and generate images that correspond to the relation, but were never seen in the training set.
7 code implementations • ICML 2017 • Urs Bergmann, Nikolay Jetchev, Roland Vollgraf
Second, we show that the image generation with PSGANs has properties of a texture manifold: we can smoothly interpolate between samples in the structured noise space and generate novel samples, which lie perceptually between the textures of the original dataset.
3 code implementations • 24 Nov 2016 • Nikolay Jetchev, Urs Bergmann, Roland Vollgraf
Generative adversarial networks (GANs) are a recent approach to train generative models of data, which have been shown to work particularly well on image data.