Skip to Main content Skip to Navigation
Conference papers

A Neural Network with Adversarial Loss for Light Field Synthesis from a Single Image

Simon Evain 1 Christine Guillemot 1
1 Sirocco - Analysis representation, compression and communication of visual data
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : This paper describes a lightweight neural network architecture with an adversarial loss for generating a full light field from one single image. The method is able to estimate disparity maps and automatically identify occluded regions from one single image thanks to a disparity confidence map based on forward-backward consistency checks. The disparity confidence map also controls the use of an adversarial loss for occlusion handling. The approach outperforms reference methods when trained and tested on light field data. Besides, we also designed the method so that it can efficiently generate a full light field from one single image, even when trained only on stereo data. This allows us to generalize our approach for view synthesis to more diverse data and semantics.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-03024210
Contributor : Christine Guillemot <>
Submitted on : Wednesday, November 25, 2020 - 5:18:01 PM
Last modification on : Friday, November 27, 2020 - 3:11:56 AM

File

VISAPP.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03024210, version 1

Citation

Simon Evain, Christine Guillemot. A Neural Network with Adversarial Loss for Light Field Synthesis from a Single Image. VISAPP 2021 - 16th International Conference on Computer Vision Theory and Applications, Feb 2021, Vienna, Austria. ⟨hal-03024210⟩

Share

Metrics

Record views

58

Files downloads

126