Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Pontes, Jhony K."'
Autor:
Michalkiewicz, Mateusz, Pontes, Jhony K., Jack, Dominic, Baktashmotlagh, Mahsa, Eriksson, Anders
Existing 3D surface representation approaches are unable to accurately classify pixels and their orientation lying on the boundary of an object. Thus resulting in coarse representations which usually require post-processing steps to extract 3D surfac
Externí odkaz:
http://arxiv.org/abs/1901.06802
Autor:
Jack, Dominic, Pontes, Jhony K., Sridharan, Sridha, Fookes, Clinton, Shirazi, Sareh, Maire, Frederic, Eriksson, Anders
Publikováno v:
Asian Conference on Computer Vision (ACCV) 2018
Representing 3D shape in deep learning frameworks in an accurate, efficient and compact manner still remains an open challenge. Most existing work addresses this issue by employing voxel-based representations. While these approaches benefit greatly f
Externí odkaz:
http://arxiv.org/abs/1803.10932
Autor:
Pontes, Jhony K., Kong, Chen, Sridharan, Sridha, Lucey, Simon, Eriksson, Anders, Fookes, Clinton
Publikováno v:
Asian Conference on Computer Vision (ACCV) 2018
One challenge that remains open in 3D deep learning is how to efficiently represent 3D data to feed deep networks. Recent works have relied on volumetric or point cloud representations, but such approaches suffer from a number of issues such as compu
Externí odkaz:
http://arxiv.org/abs/1711.10669
Autor:
Pontes, Jhony K., Kong, Chen, Eriksson, Anders, Fookes, Clinton, Sridharan, Sridha, Lucey, Simon
Publikováno v:
2017 International Conference on 3D Vision (3DV)
3D reconstruction from 2D images is a central problem in computer vision. Recent works have been focusing on reconstruction directly from a single image. It is well known however that only one image cannot provide enough information for such a recons
Externí odkaz:
http://arxiv.org/abs/1707.07360
Publikováno v:
In Pattern Recognition June 2016 54:34-51