AI RESEARCH
Efficient Learned Image Compression without Entropy Coding
arXiv CS.CV
•
ArXi:2605.23323v1 Announce Type: cross Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes the coding latency bottleneck. To overcome it, we present Entropy-Coding Free Learned Image Compression (EF-LIC), a multi-rate framework that generates compact representation by removing statistical and correlation redundancy with low coding latency. First, we