activity
20172019
most citedSurface Defect Classification in Real-Time Using Convolutional Neural Networks

8 citations · 10 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV20191 cited

Learning Quadrangulated Patches For 3D Shape Processing

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. Our method uses a novel encoding of height map based local…

cs.CV2018

DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth

Jameel Malik, Ahmed Elhayek, Fabrizio Nunnari +4

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…

cs.CV2018

Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks

Kripasindhu Sarkar, Basavaraj Hampiholi, Kiran Varanasi +1

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 locatio…

cs.CV2018

Fast Feature Extraction with CNNs with Pooling Layers

Christian Bailer, Tewodros Habtegebrial, Kiran varanasi +1

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 take…

cs.CV2018

Fast View Synthesis with Deep Stereo Vision

Tewodros Habtegebrial, Kiran Varanasi, Christian Bailer +1

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 la…

cs.CV2018

HDM-Net: Monocular Non-Rigid 3D Reconstruction with Learned Deformation Model

Vladislav Golyanik, Soshi Shimada, Kiran Varanasi +1

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 a…