Hybrid Learning-Based And Hevc-Based Coding Of Light Fields

Light fields have additional storage requirements compared to conventional image and video signals, and demand therefore an efficient representation. In order to improve coding efficiency, in this work we propose a hybrid coding scheme which combines a learning-based compression approach with a traditional video coding scheme. Their integration offers great gains at low/mid bitrates thanks to the efficient representation of the learning-based approach and is competitive at high bitrates compared to standard tools thanks to the encoding of the residual signal. The proposed approach achieves on average 38% and 31% BD rate saving compared to HEVC and JPEG Pleno transform-based codec, respectively.

[1]  Lucas Theis,et al.  Lossy Image Compression with Compressive Autoencoders , 2017, ICLR.

[2]  Waqas Ahmad,et al.  Interpreting plenoptic images as multi-view sequences for improved compression , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[3]  Touradj Ebrahimi,et al.  New Light Field Image Dataset , 2016, QoMEX 2016.

[4]  Stefan B. Williams,et al.  Linear Volumetric Focus for Light Field Cameras , 2015, TOGS.

[5]  Stefan B. Williams,et al.  Decoding, Calibration and Rectification for Lenselet-Based Plenoptic Cameras , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Hermina Petric Maretic,et al.  A graph learning approach for light field image compression , 2018, Optical Engineering + Applications.

[7]  Christine Guillemot,et al.  Light field compression using depth image based view synthesis , 2017, 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).

[8]  David Minnen,et al.  Variational image compression with a scale hyperprior , 2018, ICLR.

[9]  Frédéric Dufaux,et al.  Integral images compression scheme based on view extraction , 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

[10]  Lubomir D. Bourdev,et al.  Real-Time Adaptive Image Compression , 2017, ICML.

[11]  Peter Schelkens,et al.  JPEG Pleno light field coding technologies , 2019, Optical Engineering + Applications.

[12]  David Minnen,et al.  Variable Rate Image Compression with Recurrent Neural Networks , 2015, ICLR.

[13]  Zhibo Chen,et al.  Light field image coding via linear approximation prior , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[14]  Cristian Perra,et al.  Data formats for high efficiency coding of Lytro-Illum light fields , 2015, 2015 International Conference on Image Processing Theory, Tools and Applications (IPTA).