Asymmetric Learned Image Compression with Multi-Scale Residual Block, Importance Map, and Post-Quantization Filtering

by   Haisheng Fu, et al.

Recently, deep learning-based image compression has made signifcant progresses, and has achieved better ratedistortion (R-D) performance than the latest traditional method, H.266/VVC, in both subjective metric and the more challenging objective metric. However, a major problem is that many leading learned schemes cannot maintain a good trade-off between performance and complexity. In this paper, we propose an effcient and effective image coding framework, which achieves similar R-D performance with lower complexity than the state of the art. First, we develop an improved multi-scale residual block (MSRB) that can expand the receptive feld and is easier to obtain global information. It can further capture and reduce the spatial correlation of the latent representations. Second, a more advanced importance map network is introduced to adaptively allocate bits to different regions of the image. Third, we apply a 2D post-quantization flter (PQF) to reduce the quantization error, motivated by the Sample Adaptive Offset (SAO) flter in video coding. Moreover, We fnd that the complexity of encoder and decoder have different effects on image compression performance. Based on this observation, we design an asymmetric paradigm, in which the encoder employs three stages of MSRBs to improve the learning capacity, whereas the decoder only needs one stage of MSRB to yield satisfactory reconstruction, thereby reducing the decoding complexity without sacrifcing performance. Experimental results show that compared to the state-of-the-art method, the encoding and decoding time of the proposed method are about 17 times faster, and the R-D performance is only reduced by less than 1 H.266/VVC(4:4:4) and other recent learning-based methods. Our source code is publicly available at


page 1

page 3

page 8

page 10

page 11


Learned Variable-Rate Image Compression with Residual Divisive Normalization

Recently it has been shown that deep learning-based image compression ha...

Learned Multi-Resolution Variable-Rate Image Compression with Octave-based Residual Blocks

Recently deep learning-based image compression has shown the potential t...

Device Interoperability for Learned Image Compression with Weights and Activations Quantization

Learning-based image compression has improved to a level where it can ou...

Image Compression with Recurrent Neural Network and Generalized Divisive Normalization

Image compression is a method to remove spatial redundancy between adjac...

EVC: Towards Real-Time Neural Image Compression with Mask Decay

Neural image compression has surpassed state-of-the-art traditional code...

Deep Optimized Multiple Description Image Coding via Scalar Quantization Learning

In this paper, we introduce a deep multiple description coding (MDC) fra...

Neural Data-Dependent Transform for Learned Image Compression

Learned image compression has achieved great success due to its excellen...

Please sign up or login with your details

Forgot password? Click here to reset