Showing eess.IVShow all
3 papers · 1 filter
eess.IV2026
Wavefront Parallelization for Efficient Learned Image Compression
Shimon Murai, Fangzheng Lin, Kasidis Arunruangsirilert +1
Autoregressive context models are foundational for learned image compression,but they suffer from slow serial inference. Existing acceleration methods such as checkerboard context…
eess.IV2025
FlashGMM: Fast Gaussian Mixture Entropy Model for Learned Image Compression
Shimon Murai, Fangzheng Lin, Jiro Katto
High-performance learned image compression codecs require flexible probability models to fit latent representations. Gaussian Mixture Models (GMMs) were proposed to satisfy this de…
eess.IV2024
LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compression
Shimon Murai, Heming Sun, Jiro Katto
Supported by powerful generative models, low-bitrate learned image compression (LIC) models utilizing perceptual metrics have become feasible. Some of the most advanced models achi…