Zobrazeno 1 - 10
of 13
pro vyhledávání: '"David Ferstl"'
Publikováno v:
Zaguán. Repositorio Digital de la Universidad de Zaragoza
instname
instname
This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0706106dc9e442490190de53acbe235c
http://arxiv.org/abs/2104.13415
http://arxiv.org/abs/2104.13415
Publikováno v:
MFI
This paper presents an approach to data fusion from multiple depth sensors with different principles of range measurements. This concept is motivated by the observation that depth sensors exploiting different range measurement techniques have also di
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a823f89fb2d75497594d85333b2d175f
https://doi.org/10.1109/mfi.2016.7849459
https://doi.org/10.1109/mfi.2016.7849459
Publikováno v:
TU Graz
BMVC
BMVC
In this paper we present a novel method to increase the spatial resolution of depth images. We combine a deep fully convolutional network with a non-local variational method in a deep primal-dual network. The joint network computes a noise-free, high
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b0f7ee7a5bf0936cc5f98b0a50b4c5d6
http://arxiv.org/abs/1607.08569
http://arxiv.org/abs/1607.08569
Publikováno v:
BMVC
We present a novel method for an automatic calibration of modern consumer Timeof-Flight (ToF) cameras. Usually, these sensors come equipped with an integrated color camera. Albeit they deliver acquisitions at high frame rates they usually suffer from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e491b48667743ab9efbb34ffc0c4f7b1
https://doi.org/10.5244/c.29.102
https://doi.org/10.5244/c.29.102
Publikováno v:
Image Analysis ISBN: 9783319196640
SCIA
SCIA
We present in this paper a framework for articulated hand pose estimation and evaluation. Within this framework we implemented recently published methods for hand segmentation and inference of hand postures. We further propose a new approach for the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::317f521fb16c2a6865c0de1a9be9f7c5
https://doi.org/10.1007/978-3-319-19665-7_4
https://doi.org/10.1007/978-3-319-19665-7_4
Publikováno v:
3DV
In this paper we present a novel method to accurately estimate the dense 3D motion field, known as scene flow, from depth and intensity acquisitions. The method is formulated as a convex energy optimization, where the motion warping of each scene poi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4957334e6ae58432ac799e3e4a245694
https://doi.org/10.1109/3dv.2014.19
https://doi.org/10.1109/3dv.2014.19
Publikováno v:
BMVC
We present a novel method for dense variational scene flow estimation based a multiscale Ternary Census Transform in combination with a patchwise Closest Points depth data term. On the one hand, the Ternary Census Transform in the intensity data term
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93bf67a26d500ac0fc0304f7514bf741
https://doi.org/10.5244/c.28.18
https://doi.org/10.5244/c.28.18
Publikováno v:
BMVC
We present Hough Networks (HNs), a novel method that combines the idea of Hough Forests (HFs) [12] with Convolutional Neural Networks (CNNs) [18]. Similar to HFs we perform a simultaneous classification and regression on densely extracted image patch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0caeb366ceec58ab9e0058814024f45f
https://doi.org/10.5244/c.28.66
https://doi.org/10.5244/c.28.66
Publikováno v:
ICCV
In this work we present a novel method for the challenging problem of depth image up sampling. Modern depth cameras such as Kinect or Time-of-Flight cameras deliver dense, high quality depth measurements but are limited in their lateral resolution. T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bdc503862cec0d4edcbda71f75ef0af9
https://doi.org/10.1109/iccv.2013.127
https://doi.org/10.1109/iccv.2013.127
Publikováno v:
ICCP
We present a novel fusion method that combines complementary 3D and 2D imaging techniques. Consider a Time-of-Flight sensor that acquires a dense depth map on a wide depth range but with a comparably small resolution. Complementary, a stereo sensor g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2f65fcee7b0f1479c6cf8b217e59ba2b
https://doi.org/10.1109/iccphot.2013.6528305
https://doi.org/10.1109/iccphot.2013.6528305