Hybrid Learning-based and HEVC-based Coding of Light Fields

Milan Stepanov (1) , Giuseppe Valenzise (1) , Frédéric Dufaux (1)

1 L2S - Laboratoire des signaux et systèmes

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.

Mots clés: light field; deep learning; HEVC; JPEG Pleno

Domaines: Traitement des images [eess.IV]; Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Milan Stepanov, Giuseppe Valenzise, Frédéric Dufaux. Hybrid Learning-based and HEVC-based Coding of Light Fields. IEEE International Conference on Image Processing (ICIP’2020), Oct 2020, Abu Dhabi, United Arab Emirates. pp.3344-3348, ⟨10.1109/ICIP40778.2020.9190971⟩. ⟨hal-02609366⟩