English

3DM-WeConvene: Learned Image Compression with 3D Multi-Level Wavelet-Domain Convolution and Entropy Model

Computer Vision and Pattern Recognition 2025-04-08 v1 Applications

Abstract

Learned image compression (LIC) has recently made significant progress, surpassing traditional methods. However, most LIC approaches operate mainly in the spatial domain and lack mechanisms for reducing frequency-domain correlations. To address this, we propose a novel framework that integrates low-complexity 3D multi-level Discrete Wavelet Transform (DWT) into convolutional layers and entropy coding, reducing both spatial and channel correlations to improve frequency selectivity and rate-distortion (R-D) performance. Our proposed 3D multi-level wavelet-domain convolution (3DM-WeConv) layer first applies 3D multi-level DWT (e.g., 5/3 and 9/7 wavelets from JPEG 2000) to transform data into the wavelet domain. Then, different-sized convolutions are applied to different frequency subbands, followed by inverse 3D DWT to restore the spatial domain. The 3DM-WeConv layer can be flexibly used within existing CNN-based LIC models. We also introduce a 3D wavelet-domain channel-wise autoregressive entropy model (3DWeChARM), which performs slice-based entropy coding in the 3D DWT domain. Low-frequency (LF) slices are encoded first to provide priors for high-frequency (HF) slices. A two-step training strategy is adopted: first balancing LF and HF rates, then fine-tuning with separate weights. Extensive experiments demonstrate that our framework consistently outperforms state-of-the-art CNN-based LIC methods in R-D performance and computational complexity, with larger gains for high-resolution images. On the Kodak, Tecnick 100, and CLIC test sets, our method achieves BD-Rate reductions of -12.24%, -15.51%, and -12.97%, respectively, compared to H.266/VVC.

Keywords

Cite

@article{arxiv.2504.04658,
  title  = {3DM-WeConvene: Learned Image Compression with 3D Multi-Level Wavelet-Domain Convolution and Entropy Model},
  author = {Haisheng Fu and Jie Liang and Feng Liang and Zhenman Fang and Guohe Zhang and Jingning Han},
  journal= {arXiv preprint arXiv:2504.04658},
  year   = {2025}
}

Comments

13 pages

R2 v1 2026-06-28T22:48:49.350Z