Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Gärtner, Erik"'
We propose a new approach to learned optimization where we represent the computation of an optimizer's update step using a neural network. The parameters of the optimizer are then learned by training on a set of optimization tasks with the objective
Externí odkaz:
http://arxiv.org/abs/2212.01055
We focus on the task of estimating a physically plausible articulated human motion from monocular video. Existing approaches that do not consider physics often produce temporally inconsistent output with motion artifacts, while state-of-the-art physi
Externí odkaz:
http://arxiv.org/abs/2205.12292
We introduce DiffPhy, a differentiable physics-based model for articulated 3d human motion reconstruction from video. Applications of physics-based reasoning in human motion analysis have so far been limited, both by the complexity of constructing ad
Externí odkaz:
http://arxiv.org/abs/2205.12256
We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations which, in turn, are used to refine their visual perception capabilities.
Externí odkaz:
http://arxiv.org/abs/2112.14084
We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation. While accurate on some benchmarks
Externí odkaz:
http://arxiv.org/abs/2012.09503
Most 3d human pose estimation methods assume that input -- be it images of a scene collected from one or several viewpoints, or from a video -- is given. Consequently, they focus on estimates leveraging prior knowledge and measurement by fusing infor
Externí odkaz:
http://arxiv.org/abs/2001.02024
Autor:
Gärtner, Erik
Publikováno v:
Dissertation; (70) (2023)
Perceiving humans is an important and complex problem within computervision. Its significance is derived from its numerous applications, suchas human-robot interaction, virtual reality, markerless motion capture,and human tracking for autonomous driv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1110::038e0078381dd97d6b58dee26909009f
https://lup.lub.lu.se/record/439c532f-bc74-4863-9057-74892d32d674
https://lup.lub.lu.se/record/439c532f-bc74-4863-9057-74892d32d674
Autor:
Gärtner, Erika-Lotte
Berlin, Med. Diss. v. 23. April 1941.
Externí odkaz:
http://catalogue.bnf.fr/ark:/12148/cb32138404v