PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Framework
This work addresses the speed bottleneck for AI-based image compression, making it practical for commercial use where high throughput is required.
The paper tackles the low throughput of generative model-based image lossless compression, which limits real-world applications, and proposes PILC, an end-to-end GPU-oriented framework that achieves 200 MB/s compression and decompression speeds, 10 times faster than previous methods, while compressing 30% better than PNG.
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.