• Corpus ID: 69370873

Context-adaptive Entropy Model for End-to-end Optimized Image Compression

  title={Context-adaptive Entropy Model for End-to-end Optimized Image Compression},
  author={Jooyoung Lee and Seunghyun Cho and Seunghwa Beack},
  booktitle={International Conference on Learning Representations},
We propose a context-adaptive entropy model for use in end-to-end optimized image compression. Our model exploits two types of contexts, bit-consuming contexts and bit-free contexts, distinguished based upon whether additional bit allocation is required. Based on these contexts, we allow 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… 

Spatial-Channel Context-Based Entropy Modeling for End-to-end Optimized Image Compression

A novel entropy model based on spatial-channel contexts for end-to-end optimized image compression that jointly leverages spatial structural dependencies and channel-wise correlations to improve the probabilistic estimation of latent representations.

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

End-to-end Optimized Image Compression with Attention Mechanism

This work presents an end-to-end trainable image compression framework based on variational autoencoder, which can generate the highest PSNR and MS-SSIM for low bit-rate compression competition, and cost the lowest bytes for transparent 40db competition.

A Spatial RNN Codec for End-to-End Image Compression

This paper proposes a fast yet effective method for end-to-end image compression by incorporating a novel spatial recurrent neural network and provides a 26.73% bits-reduction than High Efficiency Video Coding (HEVC), which is the current official state-of-the-art video codec.

Learned Image Compression with Channel-Wise Grouped Context Modeling

This paper proposes a novel framework for learned image compression with channel-wise grouped context modeling that achieves competitive performance with a significantly reduced decoding complexity in comparison to 3-D context models.

Deep Image Compression with Residual Learning

An end-to-end image compression framework based on deep residual learning is proposed, which outperforms JPEG and JPEG2000 by PSNR and MS-SSIM at low BPP (bit per pixel).

A Unified End-to-End Framework for Efficient Deep Image Compression

Experimental results demonstrate that the proposed approach outperforms the current state-of-the-art image compression methods and is up to more than 150 times faster in terms of decoding speed when compared with Minnen's method.

Learning Accurate Entropy Model with Global Reference for Image Compression

A novel Global Reference Model for image compression is proposed to effectively leverage both the local and the global context information, leading to an enhanced compression rate.

Content-oriented learned image compression

This paper proposes a content-oriented image compression method, which handles different kinds of image contents with different strategies, and achieves competitive subjective results compared with state-of-the-art end-to-end learned image compression methods or classic methods.

End-to-End Image Compression via Attention-Guided Information-Preserving Module

This work designs an information-preserving compression framework using the attention mechanism, where the dual-branch architecture is utilized to prevent changes in data distribution and a cross-channel progressive enhancement network is designed by taking advantage of the relations among different channels.



Variational image compression with a scale hyperprior

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).

Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks

A method for lossy image compression based on recurrent, convolutional neural networks that outperforms BPG, WebP, JPEG2000, and JPEG as measured by MS-SSIM is proposed and it is shown that training with a pixel-wise loss weighted by SSIM increases reconstruction quality according to multiple metrics.

Lossy Image Compression with Compressive Autoencoders

It is shown that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approaches based on RNNs, and furthermore computationally efficient thanks to a sub-pixel architecture, which makes it suitable for high-resolution images.

Real-Time Adaptive Image Compression

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.

Full Resolution Image Compression with Recurrent Neural Networks

This is the first neural network architecture that is able to outperform JPEG at image compression across most bitrates on the rate-distortion curve on the Kodak dataset images, with and without the aid of entropy coding.

Generative Compression

The concept of generative compression, the compression of data using generative models, is described and it is suggested that it is a direction worth pursuing to produce more accurate and visually pleasing reconstructions at deeper compression levels for both image and video data.

End-to-end Optimized Image Compression

Across an independent set of test images, it is found that the optimized method generally exhibits better rate-distortion performance than the standard JPEG and JPEG 2000 compression methods, and a dramatic improvement in visual quality is observed, supported by objective quality estimates using MS-SSIM.

Generative Adversarial Networks for Extreme Learned Image Compression

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.

Compression Artifacts Reduction by a Deep Convolutional Network

A compact and efficient network for seamless attenuation of different compression artifacts is formulated and it is demonstrated that a deeper model can be effectively trained with the features learned in a shallow network.

High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis

This work proposes a multi-scale neural patch synthesis approach based on joint optimization of image content and texture constraints, which not only preserves contextual structures but also produces high-frequency details by matching and adapting patches with the most similar mid-layer feature correlations of a deep classification network.