Translator Disclaimer
17 September 2018 Steered mixture-of-experts for light field video coding
Author Affiliations +
Steered Mixture-of-Experts (SMoE) is a novel framework for representing multidimensional image modalities. In this paper, we propose a coding methodology for SMoE models that is readily extendable to any dimensional SMoE model, thus representing any image modality of any dimension. We evaluate the coding performance of SMoE models of light field video, a 5D image modality, i.e. time, two angular, and two spatial dimensions. The coding consists of the exploiting the redundancy between the parameters of SMoE models, i.e. a set of multivariate Gaussian distributions. We compare the performance of three multi-view HEVC (MV-HEVC) configurations that differ in terms of random access. Each subaperture view from the light field video is interpreted as a single view in MV-HEVC. Experiments validate that excellent coding performance compared to MV-HEVC for low- to midrange bitrates in terms of PSNR and SSIM with bitrate savings up to 75%.
Conference Presentation
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Vasileios Avramelos, Ignace Saenen, Ruben Verhack, Glenn Van Wallendael, Peter Lambert, and Thomas Sikora "Steered mixture-of-experts for light field video coding", Proc. SPIE 10752, Applications of Digital Image Processing XLI, 107520B (17 September 2018);


On lossless coding for HEVC
Proceedings of SPIE (February 20 2013)
Region based time varying image coding at low bit rate...
Proceedings of SPIE (April 20 1995)
Adaptive color subsampling of images
Proceedings of SPIE (October 21 1993)
Effects of dynamic quantization noise on video quality
Proceedings of SPIE (May 18 1999)
Foreground/background video coding using H.261
Proceedings of SPIE (January 08 1998)

Back to Top