A 3D Convolutional Neural Network for Light Field Depth Estimation

Ágota Faluvégi, Quentin Bolsée, Sergiu Nedevschi, Vasile Dadarlat, Adrian Munteanu

Research output: Chapter in Book/Report/Conference proceedingConference paper

Abstract

Depth estimation has always been a great challenge in the field of computer vision and machine learning. There is a rich literature focusing on depth estimation in stereo vision or in monocular imaging, while the domain of depth estimation in light field images is still in its infancy. The paper proposes a fully convolutional 3D neural network that estimates the disparity in light field images. The proposed method is parametric as it is able to adapt to input images of arbitrary size and it is lightweight and less prone to overfitting thanks to its fully convolutional nature. The experiments reveal competitive results against the state of the art, demonstrating the potential offered by deep learning solutions for disparity estimation in light field images.
Original languageEnglish
Title of host publication 2019 International Conference on 3D Immersion (IC3D)
Pages1-5
Number of pages5
Publication statusPublished - 30 Jan 2020
Event 2019 International Conference on 3D Immersion (IC3D) - Brussels, Belgium
Duration: 11 Dec 2019 → …

Conference

Conference 2019 International Conference on 3D Immersion (IC3D)
CountryBelgium
CityBrussels
Period11/12/19 → …

Fingerprint

Dive into the research topics of 'A 3D Convolutional Neural Network for Light Field Depth Estimation'. Together they form a unique fingerprint.

Cite this