LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression

TL;DR

This paper introduces LLIC, a novel learned image compression method using large receptive field transform coding with adaptive weights, achieving state-of-the-art results by reducing redundancy and enhancing expressiveness.

Contribution

The paper proposes the first large kernel-based depth-wise convolutions with adaptive weight generation and an adaptive channel-wise bit allocation strategy for improved learned image compression.

Findings

Reduces BD-Rate by approximately 9.5-11% on Kodak datasets.

Achieves state-of-the-art performance with better performance-complexity trade-offs.

Outperforms existing transform coding methods in learned image compression.

Abstract

The effective receptive field (ERF) plays an important role in transform coding, which determines how much redundancy can be removed during transform and how many spatial priors can be utilized to synthesize textures during inverse transform. Existing methods rely on stacks of small kernels, whose ERFs remain insufficiently large, or heavy non-local attention mechanisms, which limit the potential of high-resolution image coding. To tackle this issue, we propose Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression (LLIC). Specifically, for the first time in the learned image compression community, we introduce a few large kernelbased depth-wise convolutions to reduce more redundancy while maintaining modest complexity. Due to the wide range of image diversity, we further propose a mechanism to augment convolution adaptability through the self-conditioned generation of weights. The large kernels cooperate with non-linear embedding and gate mechanisms for better expressiveness and lighter pointwise interactions. Our investigation extends to refined training methods that unlock the full potential of these large kernels. Moreover, to promote more dynamic inter-channel interactions, we introduce an adaptive channel-wise bit allocation strategy that autonomously generates channel importance factors in a self-conditioned manner. To demonstrate the effectiveness of the proposed transform coding, we align the entropy model to compare with existing transform methods and obtain models LLIC-STF, LLIC-ELIC, and LLIC-TCM. Extensive experiments demonstrate that our proposed LLIC models have significant improvements over the corresponding baselines and reduce the BD-Rate by 9.49%, 9.47%, 10.94% on Kodak over VTM-17.0 Intra, respectively. Our LLIC models achieve state-of-the-art performances and better trade-offs between performance and complexity.