CompressAI: a PyTorch library and evaluation platform for end-to-end compression research
arXiv:2011.03029
Abstract
This paper presents CompressAI, a platform that provides custom operations, layers, models and tools to research, develop and evaluate end-to-end image and video compression codecs. In particular, CompressAI includes pre-trained models and evaluation tools to compare learned methods with traditional codecs. Multiple models from the state-of-the-art on learned end-to-end compression have thus been reimplemented in PyTorch and trained from scratch. We also report objective comparison results using PSNR and MS-SSIM metrics vs. bit-rate, using the Kodak image dataset as test set. Although this framework currently implements models for still-picture compression, it is intended to be soon extended to the video compression domain.
19 pages, 11 figures
References in corpus (5)
Cited by in corpus (34)
- Temporal Context Mining for Learned Video Compression
- Scalable Image Coding for Humans and Machines
- Deep Contextual Video Compression
- Supervised Compression for Resource-Constrained Edge Computing Systems
- Lossy Image Compression with Quantized Hierarchical VAEs
- Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning
- End-to-End Learnable Multi-Scale Feature Compression for VCM
- OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression
- HySpecNet-11k: A Large-Scale Hyperspectral Dataset for Benchmarking Learning-Based Hyperspectral Image Compression Methods
- Architectural Vision for Quantum Computing in the Edge-Cloud Continuum
- Learned Video Compression via Heterogeneous Deformable Compensation Network
- COIN: COmpression with Implicit Neural representations
- GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compression
- Transform Network Architectures for Deep Learning based End-to-End Image/Video Coding in Subsampled Color Spaces
- FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing
- Exploring Long- and Short-Range Temporal Information for Learned Video Compression
- OMR-NET: a two-stage octave multi-scale residual network for screen content image compression
- FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression
- Generalized Gaussian Model for Learned Image Compression
- LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression
- A Cross Channel Context Model for Latents in Deep Image Compression
- Enhanced Invertible Encoding for Learned Image Compression
- Variational Bayes image restoration with compressive autoencoders
- Comprehensive Complexity Assessment of Emerging Learned Image Compression on CPU and GPU
- Unlocking the Potential of Digital Pathology: Novel Baselines for Compression
- Learning-Based Conditional Image Coder Using Color Separation
- Channel-wise Feature Decorrelation for Enhanced Learned Image Compression
- Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform
- End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization
- A Combined Deep Learning based End-to-End Video Coding Architecture for YUV Color Space
- Learned Video Compression with Residual Prediction and Loop Filter
- Region of Interest Loss for Anonymizing Learned Image Compression
- Online Meta Adaptation for Variable-Rate Learned Image Compression
- Compressing Sensor Data for Remote Assistance of Autonomous Vehicles using Deep Generative Models