Checkerboard Context Model for Efficient Learned Image Compression

03/29/2021
by   Dailan He, et al.
0

For learned image compression, the autoregressive context model is proved effective in improving the rate-distortion (RD) performance. Because it helps remove spatial redundancies among latent representations. However, the decoding process must be done in a strict scan order, which breaks the parallelization. We propose a parallelizable checkerboard context model (CCM) to solve the problem. Our two-pass checkerboard context calculation eliminates such limitations on spatial locations by re-organizing the decoding order. Speeding up the decoding process more than 40 times in our experiments, it achieves significantly improved computational efficiency with almost the same rate-distortion performance. To the best of our knowledge, this is the first exploration on parallelization-friendly spatial context model for learned image compression.

READ FULL TEXT

page 4

page 7

page 14

research
02/18/2023

Multistage Spatial Context Models for Learned Image Compression

Recent state-of-the-art Learned Image Compression methods feature spatia...
research
09/07/2022

Learned Image Compression with Generalized Octave Convolution and Cross-Resolution Parameter Estimation

The application of the context-adaptive entropy model significantly impr...
research
05/12/2023

Exploring the Rate-Distortion-Complexity Optimization in Neural Image Compression

Despite a short history, neural image codecs have been shown to surpass ...
research
12/26/2022

Learned Lossless Image Compression Through Interpolation With Low Complexity

With the increasing popularity of deep learning in image processing, man...
research
01/13/2022

Parallel Neural Local Lossless Compression

The recently proposed Neural Local Lossless Compression (NeLLoC), which ...
research
07/17/2020

Channel-wise Autoregressive Entropy Models for Learned Image Compression

In learning-based approaches to image compression, codecs are developed ...
research
06/25/2023

Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compression

In this work, we introduce Efficient Contextformer (eContextformer) for ...

Please sign up or login with your details

Forgot password? Click here to reset