Evaluating the Practicality of Learned Image Compression

TL;DR

This paper presents a neural image compression method optimized for efficiency using neural architecture search, quantization, and engineering techniques, achieving high visual quality and real-time speeds on GPUs and CPUs.

Contribution

It introduces an efficient learned image compression framework with optimized neural architecture and implementation techniques, enabling real-time performance and superior visual quality.

Findings

Achieves higher MS-SSIM than JPEG, JPEG XL, and AVIF across bit rates.

Runs at 145 fps encoding and 208 fps decoding on Tesla T4 GPU for 1080p images.

Comparable latency to JPEG XL on CPU.

Abstract

Learned image compression has achieved extraordinary rate-distortion performance in PSNR and MS-SSIM compared to traditional methods. However, it suffers from intensive computation, which is intolerable for real-world applications and leads to its limited industrial application for now. In this paper, we introduce neural architecture search (NAS) to designing more efficient networks with lower latency, and leverage quantization to accelerate the inference process. Meanwhile, efforts in engineering like multi-threading and SIMD have been made to improve efficiency. Optimized using a hybrid loss of PSNR and MS-SSIM for better visual quality, we obtain much higher MS-SSIM than JPEG, JPEG XL and AVIF over all bit rates, and PSNR between that of JPEG XL and AVIF. Our software implementation of LIC achieves comparable or even faster inference speed compared to jpeg-turbo while being multiple times faster than JPEG XL and AVIF. Besides, our implementation of LIC reaches stunning throughput of 145 fps for encoding and 208 fps for decoding on a Tesla T4 GPU for 1080p images. On CPU, the latency of our implementation is comparable with JPEG XL.