Dynamic Kernel-Based Adaptive Spatial Aggregation for Learned Image Compression

by   Huairui Wang, et al.

Learned image compression methods have shown superior rate-distortion performance and remarkable potential compared to traditional compression methods. Most existing learned approaches use stacked convolution or window-based self-attention for transform coding, which aggregate spatial information in a fixed range. In this paper, we focus on extending spatial aggregation capability and propose a dynamic kernel-based transform coding. The proposed adaptive aggregation generates kernel offsets to capture valid information in the content-conditioned range to help transform. With the adaptive aggregation strategy and the sharing weights mechanism, our method can achieve promising transform capability with acceptable model complexity. Besides, according to the recent progress of entropy model, we define a generalized coarse-to-fine entropy model, considering the coarse global context, the channel-wise, and the spatial context. Based on it, we introduce dynamic kernel in hyper-prior to generate more expressive global context. Furthermore, we propose an asymmetric spatial-channel entropy model according to the investigation of the spatial characteristics of the grouped latents. The asymmetric entropy model aims to reduce statistical redundancy while maintaining coding efficiency. Experimental results demonstrate that our method achieves superior rate-distortion performance on three benchmarks compared to the state-of-the-art learning-based methods.


page 2

page 4

page 5

page 6

page 9

page 10

page 11


High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation

Questing for lossy image coding (LIC) with superior efficiency on both c...

SLIC: Self-Conditioned Adaptive Transform with Large-Scale Receptive Fields for Learned Image Compression

Learned image compression has achieved remarkable performance. Transform...

Multi-Context Dual Hyper-Prior Neural Image Compression

Transform and entropy models are the two core components in deep image c...

ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding

Recently, learned image compression techniques have achieved remarkable ...

On Uncertainty of Dynamic Systems via State Aggregation Coarse-Graining and State Decomposition Fine-Graining Ways

Uncertainty is an important feature of dynamic systems, and entropy has ...

Generalized Octave Convolutions for Learned Multi-Frequency Image Compression

Learned image compression has recently shown the potential to outperform...

Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain

JPEG is a popular image compression method widely used by individuals, d...

Please sign up or login with your details

Forgot password? Click here to reset