Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Eder, Marc"'
Despite remarkable improvements in speed and accuracy, convolutional neural networks (CNNs) still typically operate as monolithic entities at inference time. This poses a challenge for resource-constrained practical applications, where both computati
Externí odkaz:
http://arxiv.org/abs/2012.03153
In this work, we propose "tangent images," a spherical image representation that facilitates transferable and scalable $360^\circ$ computer vision. Inspired by techniques in cartography and computer graphics, we render a spherical image to a set of d
Externí odkaz:
http://arxiv.org/abs/1912.09390
In this work we present a method to train a plane-aware convolutional neural network for dense depth and surface normal estimation as well as plane boundaries from a single indoor $360^\circ$ image. Using our proposed loss function, our network outpe
Externí odkaz:
http://arxiv.org/abs/1907.00939
We present a versatile formulation of the convolution operation that we term a "mapped convolution." The standard convolution operation implicitly samples the pixel grid and computes a weighted sum. Our mapped convolution decouples these two componen
Externí odkaz:
http://arxiv.org/abs/1906.11096
Autor:
Eder, Marc, Frahm, Jan-Michael
Applying convolutional neural networks to spherical images requires particular considerations. We look to the millennia of work on cartographic map projections to provide the tools to define an optimal representation of spherical images for the convo
Externí odkaz:
http://arxiv.org/abs/1905.08409
Autor:
Eder, Marc
For tasks on central-perspective images, convolutional neural networks have been a revolutionary innovation. However, their performance degrades as the amount of geometric image distortion increases. This limitation is particularly evident for 360°
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::55f1cb58491736d3d20948aad64b40f1
Autor:
Eder, Marcus.
Publikováno v:
kostenfrei.
München, Universiẗat, Diss., 2007.
Externí odkaz:
http://d-nb.info/991061497/34
http://edoc.ub.uni-muenchen.de/7584/1/Eder_Marcus.pdf
http://edoc.ub.uni-muenchen.de/7584/
http://edoc.ub.uni-muenchen.de/7584/1/Eder_Marcus.pdf
http://edoc.ub.uni-muenchen.de/7584/
