Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Varanasi, Kiran"'
Surface inspection systems are an important application domain for computer vision, as they are used for defect detection and classification in the manufacturing industry. Existing systems use hand-crafted features which require extensive domain know
Externí odkaz:
http://arxiv.org/abs/1904.04671
We propose a system for surface completion and inpainting of 3D shapes using generative models, learnt on local patches. Our method uses a novel encoding of height map based local patches parameterized using 3D mesh quadrangulation of the low resolut
Externí odkaz:
http://arxiv.org/abs/1903.10885
Autor:
Malik, Jameel, Elhayek, Ahmed, Nunnari, Fabrizio, Varanasi, Kiran, Tamaddon, Kiarash, Heloir, Alexis, Stricker, Didier
Articulated hand pose and shape estimation is an important problem for vision-based applications such as augmented reality and animation. In contrast to the existing methods which optimize only for joint positions, we propose a fully supervised deep
Externí odkaz:
http://arxiv.org/abs/1808.09208
We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs. We represent 3D shapes as multi-layered height-maps (MLH) where at each grid location, we store multiple instances of height maps, thereby representing 3D
Externí odkaz:
http://arxiv.org/abs/1807.08485
In recent years, many publications showed that convolutional neural network based features can have a superior performance to engineered features. However, not much effort was taken so far to extract local features efficiently for a whole image. In t
Externí odkaz:
http://arxiv.org/abs/1805.03096
Novel view synthesis is an important problem in computer vision and graphics. Over the years a large number of solutions have been put forward to solve the problem. However, the large-baseline novel view synthesis problem is far from being "solved".
Externí odkaz:
http://arxiv.org/abs/1804.09690
Monocular dense 3D reconstruction of deformable objects is a hard ill-posed problem in computer vision. Current techniques either require dense correspondences and rely on motion and deformation cues, or assume a highly accurate reconstruction (refer
Externí odkaz:
http://arxiv.org/abs/1803.10193
We propose a novel 3D shape parameterization by surface patches, that are oriented by 3D mesh quadrangulation of the shape. By encoding 3D surface detail on local patches, we learn a patch dictionary that identifies principal surface features of the
Externí odkaz:
http://arxiv.org/abs/1709.06868
Learning based approaches have not yet achieved their full potential in optical flow estimation, where their performance still trails heuristic approaches. In this paper, we present a CNN based patch matching approach for optical flow estimation. An
Externí odkaz:
http://arxiv.org/abs/1607.08064
Autor:
Varanasi, Kiran
Space-time models (or 4D models) are descriptions of dynamic activities of the real world, that can be stored, analyzed by computers and visualized at distance. Digital imaging and computing technologies of today have matured to a level capable of re
Externí odkaz:
http://tel.archives-ouvertes.fr/tel-00569147
http://tel.archives-ouvertes.fr/docs/00/56/91/47/PDF/Thesis.pdf
http://tel.archives-ouvertes.fr/docs/00/56/91/47/PDF/Thesis.pdf