论文标题
评估学习图像压缩的实用性
Evaluating the Practicality of Learned Image Compression
论文作者
论文摘要
与传统方法相比，学到的图像压缩已在PSNR和MS-SSIM中取得了非同寻常的速率延伸性能。但是，它遭受了密集的计算，这对于现实世界的应用是无法忍受的，目前导致其工业应用有限。在本文中，我们将神经体系结构搜索（NAS）介绍给设计具有较低延迟的更有效网络，并利用量化以加速推理过程。同时，已经为提高效率做出了工程努力。使用PSNR和MS-SSIM的混合损失优化，以提高视觉质量，我们获得了比JPEG，JPEG XL和AVIF更高的MS-SSIM，而JPEG XL和AVIF之间获得了PSNR。与JPEG-Turbo相比，我们的LIC的软件实现实现了可比较甚至更快的推理速度，而多次比JPEG XL和AVIF更快。此外，我们的LIC实施达到了145 fps的惊人吞吐量，用于编码的145 fps和208 fps用于在Tesla T4 GPU上以1080p图像解码。在CPU上，我们实施的延迟与JPEG XL相当。
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.
