EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for
Depth from Light Field Images

EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Images

6 April 2018

In So Kweon

Papers citing "EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Images"

6 / 6 papers shown

Title
Learning to Synthesize a 4D RGBD Light Field from a Single Image Pratul P. Srinivasan Tongzhou Wang Ashwin Sreelal R. Ramamoorthi Ren Ng 3DV 57 238 0 10 Aug 2017
Learning-Based View Synthesis for Light Field Cameras N. Kalantari Tingxian Wang R. Ramamoorthi 3DV 124 683 0 09 Sep 2016
A 4D Light-Field Dataset and CNN Architectures for Material Recognition Tingxian Wang Jun-Yan Zhu Hiroaki Ebi Manmohan Chandraker Alexei A. Efros R. Ramamoorthi 3DV 49 187 0 24 Aug 2016
Fully Convolutional Networks for Semantic Segmentation Evan Shelhamer Jonathan Long Trevor Darrell VOS SSeg 730 37,843 0 20 May 2016
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation N. Mayer Eddy Ilg Philip Häusser Philipp Fischer Daniel Cremers Alexey Dosovitskiy Thomas Brox 3DPC 61 2,644 0 07 Dec 2015
FlowNet: Learning Optical Flow with Convolutional Networks Philipp Fischer Alexey Dosovitskiy Eddy Ilg Philip Häusser C. Hazirbas Vladimir Golkov Patrick van der Smagt Daniel Cremers Thomas Brox 3DPC 308 4,172 0 26 Apr 2015