PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Framework

TL;DR

PILC is a GPU-accelerated neural image lossless compression framework achieving 200 MB/s, significantly faster than previous methods, while maintaining better compression ratios than PNG, facilitating real-world application deployment.

Contribution

This work introduces PILC, a novel end-to-end neural compression framework that combines an auto-regressive model with VQ-VAE and a low complexity entropy coder for high-speed, high-quality lossless image compression.

Findings

Achieves 200 MB/s compression and decompression speed on a single GPU.

Outperforms PNG by 30% in compression ratio across multiple datasets.

Demonstrates potential for AI-based compression in commercial applications.

Abstract

Generative model based image lossless compression algorithms have seen a great success in improving compression ratio. However, the throughput for most of them is less than 1 MB/s even with the most advanced AI accelerated chips, preventing them from most real-world applications, which often require 100 MB/s. In this paper, we propose PILC, an end-to-end image lossless compression framework that achieves 200 MB/s for both compression and decompression with a single NVIDIA Tesla V100 GPU, 10 times faster than the most efficient one before. To obtain this result, we first develop an AI codec that combines auto-regressive model and VQ-VAE which performs well in lightweight setting, then we design a low complexity entropy coder that works well with our codec. Experiments show that our framework compresses better than PNG by a margin of 30% in multiple datasets. We believe this is an important step to bring AI compression forward to commercial use.