no code implementations • 7 Apr 2019 • Selim Arikan, Kiran varanasi, Didier Stricker
Surface inspection systems are an important application domain for computer vision, as they are used for defect detection and classification in the manufacturing industry.
no code implementations • 25 Mar 2019 • Kripasindhu Sarkar, Kiran varanasi, Didier Stricker
We propose a system for surface completion and inpainting of 3D shapes using generative models, learnt on local patches.
no code implementations • 28 Aug 2018 • Jameel Malik, Ahmed Elhayek, Fabrizio Nunnari, Kiran varanasi, Kiarash Tamaddon, Alexis Heloir, Didier Stricker
Also, by employing a joint training strategy with real and synthetic data, we recover 3D hand mesh and pose from real images in 3. 7ms.
1 code implementation • ECCV 2018 • Kripasindhu Sarkar, Basavaraj Hampiholi, Kiran varanasi, Didier Stricker
We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs.
1 code implementation • 8 May 2018 • Christian Bailer, Tewodros Habtegebrial, Kiran varanasi, Didier Stricker
In recent years, many publications showed that convolutional neural network based features can have a superior performance to engineered features.
no code implementations • 25 Apr 2018 • Tewodros Habtegebrial, Kiran varanasi, Christian Bailer, Didier Stricker
Novel view synthesis is an important problem in computer vision and graphics.
no code implementations • 27 Mar 2018 • Vladislav Golyanik, Soshi Shimada, Kiran varanasi, Didier Stricker
Monocular dense 3D reconstruction of deformable objects is a hard ill-posed problem in computer vision.
no code implementations • 20 Sep 2017 • Kripasindhu Sarkar, Kiran varanasi, Didier Stricker
By encoding 3D surface detail on local patches, we learn a patch dictionary that identifies principal surface features of the shape.
no code implementations • CVPR 2017 • Christian Bailer, Kiran varanasi, Didier Stricker
In this paper, we present a CNN based patch matching approach for optical flow estimation.