2 papers
eess.IV2022
Edge-Aware Autoencoder Design for Real-Time Mixture-of-Experts Image Compression
Elvira Fleig, Jonas Geistert, Erik Bochinski +2
Steered-Mixtures-of-Experts (SMoE) models provide sparse, edge-aware representations, applicable to many use-cases in image processing. This includes denoising, super-resolution an…
eess.IV2022
Accelerated Deep Lossless Image Coding with Unified Paralleleized GPU Coding Architecture
Benjamin Lukas Cajus Barzen, Fedor Glazov, Jonas Geistert +1
We propose Deep Lossless Image Coding (DLIC), a full resolution learned lossless image compression algorithm. Our algorithm is based on a neural network combined with an entropy en…