Search Results for author: Urs Bergmann

Found 17 papers, 7 papers with code

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

no code implementations25 Nov 2021 Mehdi S. M. Sajjadi, Henning Meyer, Etienne Pot, Urs Bergmann, Klaus Greff, Noha Radwan, Suhani Vora, Mario Lucic, Daniel Duckworth, Alexey Dosovitskiy, Jakob Uszkoreit, Thomas Funkhouser, Andrea Tagliasacchi

In this work, we propose the Scene Representation Transformer (SRT), a method which processes posed or unposed RGB images of a new area, infers a "set-latent scene representation", and synthesises novel views, all in a single feed-forward pass.

Novel View Synthesis Semantic Segmentation

Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows

1 code implementation ICLR 2021 Kashif Rasul, Abdul-Saboor Sheikh, Ingmar Schuster, Urs Bergmann, Roland Vollgraf

In this work we model the multivariate temporal dynamics of time series via an autoregressive deep learning model, where the data distribution is represented by a conditioned normalizing flow.

Decision Making Multivariate Time Series Forecasting +3

Transform the Set: Memory Attentive Generation of Guided and Unguided Image Collages

no code implementations16 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.

Image Generation

Set Flow: A Permutation Invariant Normalizing Flow

no code implementations6 Sep 2019 Kashif Rasul, Ingmar Schuster, Roland Vollgraf, Urs Bergmann

We present a generative model that is defined on finite sets of exchangeable, potentially high dimensional, data.

A Hierarchical Bayesian Model for Size Recommendation in Fashion

no code implementations2 Aug 2019 Romain Guigourès, Yuen King Ho, Evgenii Koriagin, Abdul-Saboor Sheikh, Urs Bergmann, Reza Shirvany

We introduce a hierarchical Bayesian approach to tackle the challenging problem of size recommendation in e-commerce fashion.

A Deep Learning System for Predicting Size and Fit in Fashion E-Commerce

3 code implementations23 Jul 2019 Abdul-Saboor Sheikh, Romain Guigoures, Evgenii Koriagin, Yuen King Ho, Reza Shirvany, Roland Vollgraf, Urs Bergmann

To alleviate this problem, we propose a deep learning based content-collaborative methodology for personalized size and fit recommendation.

Collaborative Filtering Entity Embeddings

Unlabeled Disentangling of GANs with Guided Siamese Networks

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.

A Bandit Framework for Optimal Selection of Reinforcement Learning Agents

no code implementations10 Feb 2019 Andreas Merentitis, Kashif Rasul, Roland Vollgraf, Abdul-Saboor Sheikh, Urs Bergmann

This helps the bandit framework to select the best agents early, since these rewards are smoother and less sparse than the environment reward.

reinforcement-learning

Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization

5 code implementations22 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.

Image Stylization

Disentangling Multiple Conditional Inputs in GANs

2 code implementations20 Jun 2018 Gökhan Yildirim, Calvin Seward, Urs Bergmann

In this paper, we propose a method that disentangles the effects of multiple input conditions in Generative Adversarial Networks (GANs).

First Order Generative Adversarial Networks

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.

Image Generation Text Generation

GANosaic: Mosaic Creation with Generative Texture Manifolds

no code implementations1 Dec 2017 Nikolay Jetchev, Urs Bergmann, Calvin Seward

This paper presents a novel framework for generating texture mosaics with convolutional neural networks.

Texture Synthesis

The Conditional Analogy GAN: Swapping Fashion Articles on People Images

no code implementations14 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.

Learning Texture Manifolds with the Periodic Spatial GAN

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.

Image Generation Texture Synthesis

Texture Synthesis with Spatial Generative Adversarial Networks

3 code implementations24 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.

Texture Synthesis

Cannot find the paper you are looking for? You can Submit a new open access paper.