Universal Efficient Variable-Rate Neural Image Compression

  title={Universal Efficient Variable-Rate Neural Image Compression},
  author={Shan Yin and Chao Li and Youneng Bao and Yongshang Liang},
  journal={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  • Shan YinChao Li Yongshang Liang
  • Published 18 November 2021
  • Computer Science
  • ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Recently, Learning-based image compression has reached comparable performance with traditional image codecs(such as JPEG, BPG, WebP). However, computational complexity and rate flexibility are still two major challenges for its practical deployment. To tackle these problems, this paper proposes two universal modules named Energy-based Channel Gating(ECG) and Bit-rate Modulator(BM), which can be directly embedded into existing end-to-end image compression models. ECG uses dynamic pruning to… 

Figures and Tables from this paper

Exploring Structural Sparsity in Neural Image Compression

This paper proposes a simple plug-in adaptive binary channel masking (ABCM) to judge the importance of each convolution channel and introduce sparsity during training and results show that up to 7 × computation reduction and 3 × acceleration can be achieved with negligible performance drop.

Joint image compression and denoising via latent-space scalability

This paper presents a learning-based image compression framework where image denoising and compression are performed jointly, and reveals considerable bitrate savings compared to a cascade combination of a state-of-the-art codec and a state of theart denoiser.



Rate Distortion Characteristic Modeling for Neural Image Compression

This paper proposes a plugin-in module to learn the relationship between the target bit-rate and the binary representation for the latent variable of auto-encoder, and model the rate and distortion characteristic of NIC as a function of the coding parameter $\lambda$ respectively.

CBANet: Towards Complexity and Bitrate Adaptive Deep Image Compression using a Single Network

A new deep image compression framework called Complexity and Bitrate Adaptive Network (CBANet), which aims to learn one single network to support variable bitrate coding under different computational complexity constraints, and proposes a new multi-branch complexity adaptive module.

End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling

An end-to-end learnt lossy image compression approach, which is built on top of the deep nerual network (DNN)-based variational auto-encoder (VAE) structure with Non-Local Attention optimization and Improved Context modeling (NLAIC).

CompressAI: a PyTorch library and evaluation platform for end-to-end compression research

CompressAI is presented, a platform that provides custom operations, layers, models and tools to research, develop and evaluate end-to-end image and video compression codecs and is intended to be soon extended to the video compression domain.

End-to-End Optimized Versatile Image Compression With Wavelet-Like Transform

iWave++ is proposed as a new end-to-end optimized image compression scheme, in which iWave, a trained wavelet-like transform, converts images into coefficients without any information loss, and a single model supports both lossless and lossy compression.

Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation

A continuously rate adjustable learned image compression framework, Asymmetric Gained Variational Autoencoder (AG-VAE), which utilizes a pair of gain units to achieve discrete rate adaptation in one single model with a negligible additional computation and the asymmetric Gaussian entropy model for more accurate entropy estimation.

Learned Image Compression With Discretized Gaussian Mixture Likelihoods and Attention Modules

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.

Computationally Efficient Neural Image Compression

This work applies automatic network optimization techniques to reduce the computational complexity of a popular architecture used in neural image compression, analyzes the decoder complexity in execution runtime and explores the trade-offs between two distortion metrics, rate-distortion performance and run-time performance to design and research more computationally efficient Neural image compression.

Variable Rate Deep Image Compression With Modulated Autoencoder

Modulated autoencoders (MAEs) are proposed, where the representations of a shared autoencoder are adapted to the specific R-D tradeoff via a modulation network, and can achieve almost the same R- D performance of independent models with significantly fewer parameters.

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

This paper proposes an Efficient Channel Attention (ECA) module, which only involves a handful of parameters while bringing clear performance gain, and develops a method to adaptively select kernel size of 1D convolution, determining coverage of local cross-channel interaction.