Checkerboard Context Model for Efficient Learned Image Compression

By Dailan He, Yaoyan Zheng, Baochen Sun, Yan Wang, Hongwei Qin. Computer Vision and Pattern Recognition, 2021

412 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d64945650501eaccd842ed5f93fe0e8932cac50c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Lianli Gao
2. Jiangpeng He
3. Jingkuan Song
4. Feng Zhu
5. Zhihao Duan
6. Justin Yang
7. Zi Yang
8. Jackie Ma

Citations in the corpus

• QARV: Quantization-Aware ResNet VAE for Lossy Image Compression (2023, methodology): “Thisconclusionholdsforalltypesofautoregressivemodels, includingthestandard,rasterscanorderARmodel[8](fora constantimageresolution),thechannel-wiseARmodel[10], andtheCheckerboardcontextmodel[9].”
• Towards Backward-Compatible Continual Learning of Image Compression (2024, background): “Another line of research lies in designing the entropy model pz, such as autoregressive [22, 40, 41, 44] and hierarchical models [3, 14, 15, 25].”
• The Devil Is in the Details: Window-based Attention for Image Compression (2022, neutral): “Recently, learned image compression models [5,6,15–17, 19, 27 , 32, 34, 35 ] based on CNNs exhibit a fast development trend Transformer-based Model.”
• Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression (2022, background): “4Tested latencies of [16] are slightly slower than their report.”
• ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding (2022, positive): “It could be an autoregressive convolution [39] or its two-pass parallel adaption [24].”