IVCVApr 25, 2022

High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation

arXiv:2204.11448v255 citationsh-index: 14
Originality Highly original
AI Analysis

This addresses the need for efficient and high-performance image compression, with incremental improvements in speed and accuracy for applications like storage and transmission.

The paper tackles lossy image compression by proposing an adaptive neighborhood information aggregation method, achieving state-of-the-art performance across multiple datasets and offering over 60x decoding speedup compared to popular methods.

Questing for learned lossy image coding (LIC) with superior compression performance and computation throughput is challenging. The vital factor behind it is how to intelligently explore Adaptive Neighborhood Information Aggregation (ANIA) in transform and entropy coding modules. To this end, Integrated Convolution and Self-Attention (ICSA) unit is first proposed to form a content-adaptive transform to characterize and embed neighborhood information dynamically of any input. Then a Multistage Context Model (MCM) is devised to progressively use available neighbors following a pre-arranged spatial-channel order for accurate probability estimation in parallel. ICSA and MCM are stacked under a Variational AutoEncoder (VAE) architecture to derive rate-distortion optimized compact representation of input image via end-to-end learning. Our method reports state-of-the-art compression performance surpassing the VVC Intra and other prevalent LIC approaches across Kodak, CLIC, and Tecnick datasets; More importantly, our method offers $>$60$\times$ decoding speedup using a comparable-size model when compared with the most popular LIC method. All materials are made publicly accessible at https://njuvision.github.io/TinyLIC for reproducible research.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes