Checkerboard Context Model for Efficient Learned Image Compression

@article{He2021CheckerboardCM,
  title={Checkerboard Context Model for Efficient Learned Image Compression},
  author={Dailan He and Yaoyan Zheng and Baochen Sun and Yan Wang and Hongwei Qin},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021},
  pages={14766-14775}
}
  • Dailan He, Yaoyan Zheng, Hongwei Qin
  • Published 29 March 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
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… 
ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding
TLDR
This work proposes uneven channel-conditional adaptive coding, motivated by the observation of energy compaction in learned image compression, and proposes an efficient model, ELIC, to achieve state-of-the-art speed and compression ability.
Memory-Efficient Learned Image Compression with Pruned Hyperprior Module
TLDR
A novel pruning method named ERHP is proposed in this paper to efficiently reduce the memory cost of hyperprior module, while improving the network performance.
Post-Training Quantization for Cross-Platform Learned Image Compression
TLDR
This work introduces well-developed post-training quantization and makes the model inference integer-arithmetic-only, which is much simpler than presently existing training and fine-tuning based approaches yet still keeps the superior rate-distortion performance of learned image compression.
Entroformer: A Transformer-based Entropy Model for Learned Image Compression
TLDR
This work proposes a novel transformer-based entropy model, termed Entroformer, to capture long-range dependencies in probability distribution estimation effectively and efficiently and achieves state-of-the-art performance on image compression while being time-efficient.
Joint Global and Local Hierarchical Priors for Learned Image Compression
TLDR
This work proposes a novel entropy model called Information Transformer (Informer) that exploits both global and local information in a content-dependent manner using an attention mechanism and shows that Informer improves rate–distortion performance over the state-of-the-art methods on the Kodak and Tecnick datasets without the quadratic computational complexity problem.
The Devil Is in the Details: Window-based Attention for Image Compression
TLDR
This paper first extensively study the effects of multiple kinds of attention mechanisms for local features learning, then introduces a more straightforward yet effective window-based local attention block, which is very flexible which could work as a plug-and-play component to enhance CNN and Transformer models.
DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression
TLDR
This paper introduces a feature separation backbone to divide the image information into basic and scalable features, then redistribute the features channel by channel through an information rearrangement strategy, which can generate a continuously scalable bitstream via onepass encoding.
Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement
TLDR
This study embeds hybrid domain attention modules as nonlinear transformers in both the main encoder-decoder network and the hyperprior network, aiming at constructing more compact latent features and hyperpriors and then model the latent features as parametric Gaussian-scale mixture models to obtain more precise entropy estimation.
Deep Stereo Image Compression via Bi-directional Coding
TLDR
Experimental results on the InStereo2K and KITTI datasets demonstrate that the proposed BCSIC-Net can effectively reduce the inter-view redundancy and out-performs state-of-the-art methods.
High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation
TLDR
This method reports the superior compression performance surpassing the VVC Intra with ≈ 15% BD-rate improvement averaged across Kodak, CLIC and Tecnick datasets; and also demonstrates the 10 × speedup of image decoding when compared with other notable learned LIC approaches.
...
...

References

SHOWING 1-10 OF 43 REFERENCES
Channel-Wise Autoregressive Entropy Models for Learned Image Compression
TLDR
This work introduces two enhancements, channel-conditioning and latent residual prediction, that lead to network architectures with better rate-distortion performance than existing context-adaptive models while minimizing serial processing.
Learning to Inpaint for Image Compression
TLDR
Predicting the original image data from residuals in a multi-stage progressive architecture facilitates learning and leads to improved performance at approximating the original content and learning to inpaint before performing compression reduces the amount of information that must be stored to achieve a high-quality approximation.
Multi-scale and Context-adaptive Entropy Model for Image Compression
We propose an end-to-end trainable image compression framework with a multi-scale and context-adaptive entropy model, especially for low bitrate compression. Due to the success of autoregressive
Image-Dependent Local Entropy Models for Learned Image Compression
TLDR
This work presents a method for augmenting ANN-based image coders with image-dependent side information that leads to a 17.8% rate reduction over a state-of-the-art ANN- based baseline model on a standard evaluation set, and 70-98% reductions on images with low visual complexity that are poorly captured by a fixed, global entropy model.
Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression
TLDR
The promise of CCNs for entropy modeling in both lossless and lossy image compression is demonstrated and methods powered by the proposed CCNs generally achieve comparable compression performance to the state-of-the-art while being much faster.
Variational image compression with a scale hyperprior
TLDR
It is demonstrated that this model leads to state-of-the-art image compression when measuring visual quality using the popular MS-SSIM index, and yields rate-distortion performance surpassing published ANN-based methods when evaluated using a more traditional metric based on squared error (PSNR).
Learned Image Compression With Discretized Gaussian Mixture Likelihoods and Attention Modules
TLDR
This paper proposes to use discretized Gaussian Mixture Likelihoods to parameterize the distributions of latent codes, which can achieve a more accurate and flexible entropy model and achieves a state-of-the-art performance against existing learned compression methods.
Generative Adversarial Networks for Extreme Learned Image Compression
TLDR
If a semantic label map of the original image is available, the learned image compression system can fully synthesize unimportant regions in the decoded image such as streets and trees from the label map, proportionally reducing the storage cost.
Real-Time Adaptive Image Compression
TLDR
A machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time, and supplementing the approach with adversarial training specialized towards use in a compression setting.
Context-adaptive Entropy Model for End-to-end Optimized Image Compression
TLDR
The proposed context-adaptive entropy model exploits two types of contexts, bit-consuming contexts and bit-free contexts, distinguished based upon whether additional bit allocation is required, which allows the model to more accurately estimate the distribution of each latent representation with a more generalized form of the approximation models, which accordingly leads to an enhanced compression performance.
...
...