Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Bergmann, Urs"'
Autor:
Sajjadi, Mehdi S. M., Meyer, Henning, Pot, Etienne, Bergmann, Urs, Greff, Klaus, Radwan, Noha, Vora, Suhani, Lucic, Mario, Duckworth, Daniel, Dosovitskiy, Alexey, Uszkoreit, Jakob, Funkhouser, Thomas, Tagliasacchi, Andrea
Publikováno v:
CVPR 2022
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 reconstructing pre-defined 3D representations, e.g. textured meshes, or
Externí odkaz:
http://arxiv.org/abs/2111.13152
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 predictions is to assume independence between interacting time series
Externí odkaz:
http://arxiv.org/abs/2002.06103
Cutting and pasting image segments feels intuitive: the choice of source templates gives artists flexibility in recombining existing source material. Formally, this process takes an image set as input and outputs a collage of the set elements. Such s
Externí odkaz:
http://arxiv.org/abs/1910.07236
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 its favorable properties, such as being invertible and allowing for exa
Externí odkaz:
http://arxiv.org/abs/1909.02775
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-determined set of outfits. In this paper, we broaden these visualizations by
Externí odkaz:
http://arxiv.org/abs/1908.08847
Autor:
Guigourès, Romain, Ho, Yuen King, Koriagin, Evgenii, Sheikh, Abdul-Saboor, Bergmann, Urs, Shirvany, Reza
Publikováno v:
In: Proceedings of the 12th ACM Conference on Recommender Systems. ACM, 2018. S. 392-396
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 customer, and its possible return event: 1. no return, 2. returned too sma
Externí odkaz:
http://arxiv.org/abs/1908.00825
Autor:
Sheikh, Abdul-Saboor, Guigoures, Romain, Koriagin, Evgenii, Ho, Yuen King, Shirvany, Reza, Vollgraf, Roland, Bergmann, Urs
Personalized size and fit recommendations bear crucial significance for any fashion e-commerce platform. Predicting the correct fit drives customer satisfaction and benefits the business by reducing costs incurred due to size-related returns. Traditi
Externí odkaz:
http://arxiv.org/abs/1907.09844
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 practical applications, however, interactions with the environment are co
Externí odkaz:
http://arxiv.org/abs/1902.03657
Parametric generative deep models are state-of-the-art for photo and non-photo realistic image stylization. However, learning complicated image representations requires compute-intense models parametrized by a huge number of weights, which in turn re
Externí odkaz:
http://arxiv.org/abs/1811.09236
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 controlling color, texture, and shape of a generated garment image fo
Externí odkaz:
http://arxiv.org/abs/1806.07819