3DM-WeConvene: Learned Image Compression with 3D Multi-Level Wavelet-Domain Convolution and Entropy Model
By: Haisheng Fu , Jie Liang , Feng Liang and more
Potential Business Impact:
Makes pictures smaller with less detail lost.
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.
Similar Papers
3D Wavelet Convolutions with Extended Receptive Fields for Hyperspectral Image Classification
CV and Pattern Recognition
Helps computers see details in special pictures.
Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation
CV and Pattern Recognition
Teaches computers to see faster using sound waves.
LoC-LIC: Low Complexity Learned Image Coding Using Hierarchical Feature Transforms
Image and Video Processing
Makes pictures smaller using less computer power.