107 citations · 324 across the 17 of their papers we have counts for
18 papers
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformers
Maximilian Dax, Jordi Berbel, Jan Stria +2
We generate abstractions of buildings, reflecting the essential aspects of their geometry and structure, by learning to invert procedural models. We first build a dataset of abstra…
Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
Mehdi S. M. Sajjadi, Henning Meyer, Etienne Pot +10
A classical problem in computer vision is to infer a 3D scene representation from few images that can be used to render novel views at interactive rates. Previous work focuses on r…
Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows
Kashif Rasul, Abdul-Saboor Sheikh, Ingmar Schuster +2
Time series forecasting is often fundamental to scientific and engineering problems and enables decision making. With ever increasing data set sizes, a trivial solution to scale up…
Transform the Set: Memory Attentive Generation of Guided and Unguided Image Collages
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. Formally, this process takes a…
Set Flow: A Permutation Invariant Normalizing Flow
Kashif Rasul, Ingmar Schuster, Roland Vollgraf +1
We present a generative model that is defined on finite sets of exchangeable, potentially high dimensional, data. As the architecture is an extension of RealNVPs, it inherits all i…
Generating High-Resolution Fashion Model Images Wearing Custom Outfits
Gökhan Yildirim, Nikolay Jetchev, Roland Vollgraf +1
Visualizing an outfit is an essential part of shopping for clothes. Due to the combinatorial aspect of combining fashion articles, the available images are limited to a pre-determi…
A Hierarchical Bayesian Model for Size Recommendation in Fashion
Romain Guigourès, Yuen King Ho, Evgenii Koriagin +3
We introduce a hierarchical Bayesian approach to tackle the challenging problem of size recommendation in e-commerce fashion. Our approach jointly models a size purchased by a cust…
A Deep Learning System for Predicting Size and Fit in Fashion E-Commerce
Abdul-Saboor Sheikh, Romain Guigoures, Evgenii Koriagin +4
Personalized size and fit recommendations bear crucial significance for any fashion e-commerce platform. Predicting the correct fit drives customer satisfaction and benefits the bu…
A Bandit Framework for Optimal Selection of Reinforcement Learning Agents
Andreas Merentitis, Kashif Rasul, Roland Vollgraf +2
Deep Reinforcement Learning has been shown to be very successful in complex games, e.g. Atari or Go. These games have clearly defined rules, and hence allow simulation. In many pra…
Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization
Nikolay Jetchev, Urs Bergmann, Gokhan Yildirim
Parametric generative deep models are state-of-the-art for photo and non-photo realistic image stylization. However, learning complicated image representations requires compute-int…
Disentangling Multiple Conditional Inputs in GANs
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). In particular, we demonstrate our method in…
First Order Generative Adversarial Networks
Calvin Seward, Thomas Unterthiner, Urs Bergmann +2
GANs excel at learning high dimensional distributions, but they can update generator parameters in directions that do not correspond to the steepest descent direction of the object…
Stochastic Maximum Likelihood Optimization via Hypernetworks
Abdul-Saboor Sheikh, Kashif Rasul, Andreas Merentitis +1
This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employe…
GANosaic: Mosaic Creation with Generative Texture Manifolds
Nikolay Jetchev, Urs Bergmann, Calvin Seward
This paper presents a novel framework for generating texture mosaics with convolutional neural networks. Our method is called GANosaic and performs optimization in the latent noise…
The Conditional Analogy GAN: Swapping Fashion Articles on People Images
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…
Learning Texture Manifolds with the Periodic Spatial GAN
Urs Bergmann, Nikolay Jetchev, Roland Vollgraf
This paper introduces a novel approach to texture synthesis based on generative adversarial networks (GAN) (Goodfellow et al., 2014). We extend the structure of the input noise dis…
Texture Synthesis with Spatial Generative Adversarial Networks
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. In the current paper…