TU Berlin

Fachgebiet NachrichtenübertragungWiss. Veröffentlichungen

Inhalt des Dokuments

zur Navigation

Wissenschaftliche Veröffentlichungen

Quantized and Regularized Optimization for Coding Images Using Steered Mixtures-of-Experts
Zitatschlüssel 1571Jongebloed2019
Autor Rolf Jongebloed and Erik Bochinski and Lieven lange and Thomas Sikora
Buchtitel 2019 Data Compression Conference (DCC)
Jahr 2019
Zusammenfassung Compression algorithms that employ Mixtures-of-Experts depart drastically from standard hybrid block-based transform domain approaches as in JPEG and MPEG coders. In pre- vious works we introduced the concept of Steered Mixtures-of-Experts (SMoEs) to arrive at sparse representations of signals. SMoEs are gating networks trained in a machine learn- ing approach that allow individual experts to explain and harvest directional long-range correlation in the N-dimensional signal space. Previous results showed excellent potential for compression of images and videos but the reconstruction quality was mainly limited to low and medium image quality. In this paper we provide evidence that SMoEs can com- pete with JPEG2000 at mid- and high-range bit-rates. To this end we introduce a SMoE approach for compression of color images with specialized gates and steering experts. A novel machine learning approach is introduced that optimizes RD-performance of quantized SMoEs towards SSIM using fake quantization. We drastically improve our previous results and outperform JPEG by up to 42%.
Link zur Publikation Download Bibtex Eintrag



Schnellnavigation zur Seite über Nummerneingabe