Context-adaptive Entropy Model for End-to-end Optimized Image Compression
arXiv:1809.10452
Abstract
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. Based on the experimental results, the proposed method outperforms the traditional image codecs, such as BPG and JPEG2000, as well as other previous artificial-neural-network (ANN) based approaches, in terms of the peak signal-to-noise ratio (PSNR) and multi-scale structural similarity (MS-SSIM) index.
arXiv commentPublished as a conference paper at ICLR 2019. The test code, evaluation results and reconstructed images are publicly available at https://github.com/JooyoungLeeETRI/CA_Entropy_Model
Cited by in corpus (60)
- High-Fidelity Generative Image Compression
- Causal Contextual Prediction for Learned Image Compression
- Scalable Image Coding for Humans and Machines
- Deep Learning-Based Video Coding: A Review and A Case Study
- Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
- MLIC: Multi-Reference Entropy Model for Learned Image Compression
- A Unified End-to-End Framework for Efficient Deep Image Compression
- Improving Inference for Neural Image Compression
- Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks
- Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules
- Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning
- Advancing Learned Video Compression with In-loop Frame Prediction
- An End-to-End Joint Learning Scheme of Image Compression and Quality Enhancement with Improved Entropy Minimization
- Learning Accurate Entropy Model with Global Reference for Image Compression
- Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression
- LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression
- Enhanced Standard Compatible Image Compression Framework based on Auxiliary Codec Networks
- Generalized Octave Convolutions for Learned Multi-Frequency Image Compression
- Deep Perceptual Compression
- Human Perceptual Evaluations for Image Compression
- Modeling Lost Information in Lossy Image Compression
- High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation
- Checkerboard Context Model for Efficient Learned Image Compression
- OpenDVC: An Open Source Implementation of the DVC Video Compression Method
- BINet: a binary inpainting network for deep patch-based image compression
- Advancing The Rate-Distortion-Computation Frontier For Neural Image Compression
- A Cross Channel Context Model for Latents in Deep Image Compression
- Learning to Compress Videos without Computing Motion
- Disparity-based Stereo Image Compression with Aligned Cross-View Priors
- Enhanced Invertible Encoding for Learned Image Compression
- DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedback
- Soft then Hard: Rethinking the Quantization in Neural Image Compression
- Spatiotemporal Entropy Model is All You Need for Learned Video Compression
- A 1Mb mixed-precision quantized encoder for image classification and patch-based compression
- Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems
- Conditional Entropy Coding for Efficient Video Compression
- Slimmable Compressive Autoencoders for Practical Neural Image Compression
- Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform
- Neural Video Coding using Multiscale Motion Compensation and Spatiotemporal Context Model
- Learned Block-based Hybrid Image Compression
- Channel-Level Variable Quantization Network for Deep Image Compression
- End-to-end Optimized Video Compression with MV-Residual Prediction
- Learning End-to-End Lossy Image Compression: A Benchmark
- DSIC: Deep Stereo Image Compression
- Convolutional Transformer-Based Image Compression
- Learned Lossless Image Compression with a HyperPrior and Discretized Gaussian Mixture Likelihoods
- Thousand to One: Semantic Prior Modeling for Conceptual Coding
- Online Meta Adaptation for Variable-Rate Learned Image Compression
- Saliency Driven Perceptual Image Compression
- Learning Scalable -constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression
- ModeNet: Mode Selection Network For Learned Video Coding
- Deep motion estimation for parallel inter-frame prediction in video compression
- Learning to Learn to Compress
- Improved Image Coding Autoencoder With Deep Learning
- Neural Weight Step Video Compression
- Image Compression with Recurrent Neural Network and Generalized Divisive Normalization
- Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization
- Learned Image Compression with Separate Hyperprior Decoders
- Generative Memorize-Then-Recall framework for low bit-rate Surveillance Video Compression
- Low Bitrate Image Compression with Discretized Gaussian Mixture Likelihoods