Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Lehrmann, Andreas"'
Autor:
Liu, Siqi, Lehrmann, Andreas
Deep learning has shown impressive results in a variety of time series forecasting tasks, where modeling the conditional distribution of the future given the past is the essence. However, when this conditional distribution is non-stationary, it poses
Externí odkaz:
http://arxiv.org/abs/2209.08411
Particle filtering is a standard Monte-Carlo approach for a wide range of sequential inference tasks. The key component of a particle filter is a set of particles with importance weights that serve as a proxy of the true posterior distribution of som
Externí odkaz:
http://arxiv.org/abs/2209.00173
Normalizing flows model a complex target distribution in terms of a bijective transform operating on a simple base distribution. As such, they enable tractable computation of a number of important statistical quantities, particularly likelihoods and
Externí odkaz:
http://arxiv.org/abs/2202.11322
Partial observations of continuous time-series dynamics at arbitrary time stamps exist in many disciplines. Fitting this type of data using statistical models with continuous dynamics is not only promising at an intuitive level but also has practical
Externí odkaz:
http://arxiv.org/abs/2106.15580
Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a novel spatio-
Externí odkaz:
http://arxiv.org/abs/2006.14727
Normalizing flows transform a simple base distribution into a complex target distribution and have proved to be powerful models for data generation and density estimation. In this work, we propose a novel type of normalizing flow driven by a differen
Externí odkaz:
http://arxiv.org/abs/2002.10516
Human activity videos involve rich, varied interactions between people and objects. In this paper we develop methods for generating such videos -- making progress toward addressing the important, open problem of video generation in complex scenes. In
Externí odkaz:
http://arxiv.org/abs/1912.02401
Autor:
Lombardi, Stephen, Simon, Tomas, Saragih, Jason, Schwartz, Gabriel, Lehrmann, Andreas, Sheikh, Yaser
Publikováno v:
ACM Transactions on Graphics (SIGGRAPH 2019) 38, 4, Article 65
Modeling and rendering of dynamic scenes is challenging, as natural scenes often contain complex phenomena such as thin structures, evolving topology, translucency, scattering, occlusion, and biological motion. Mesh-based reconstruction and tracking
Externí odkaz:
http://arxiv.org/abs/1906.07751
Relighting is an essential step in realistically transferring objects from a captured image into another environment. For example, authentic telepresence in Augmented Reality requires faces to be displayed and relit consistent with the observer's sce
Externí odkaz:
http://arxiv.org/abs/1906.03355
We introduce the first work to tackle the image retrieval problem as a continuous operation. While the proposed approaches in the literature can be roughly categorized into two main groups: category- and instance-based retrieval, in this work we show
Externí odkaz:
http://arxiv.org/abs/1812.00202