arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.15870eess.IVcs.CVcs.LG
收藏

循环图像压缩:CIC

CIC: Circular Image Compression

Yangzhou University(扬州大学);Shanghai University of Traditional Chinese Medicine(上海中医药大学);Institut Supérieur d'Électronique de Paris(巴黎高等电子学院);Sorbonne University(索邦大学);Beijing University of Aeronautics and Astronautics(北京航空航天大学);Westlake University(西湖大学);Polytechnique Montreal(蒙特利尔高等理工学院)

Honggui Li, Sinan Chen, Dingtai Li, Zhengyang Zhang, Nahid Md Lokman Hossain, Xinfeng Xu, Yinlu Qin, Ruobing Wang, Maria Trocan, Dimitri Galayko, Amara Amara, Mohamad Sawan

AI总结:

本文提出循环图像压缩(CIC)方法,通过闭环架构提升LIC的动态和静态性能,实验表明其在重建能力和样本外测试图像处理方面优于现有方法。

摘要:

学习图像压缩(LIC)目前是最先进的方法。然而,LIC在训练和测试图像之间的固有差异导致性能有所下降。特别是对于样本外、分布外或领域外的测试图像,LIC的性能会显著下降。经典的LIC是一种串行图像压缩(SIC)方法,它使用开环架构,包含串行编码和解码单元。然而,根据自动控制系统的原则,闭环架构有潜力提高LIC的动态和静态性能。因此,提出了一种闭环编码和解码元素的循环图像压缩(CIC)方法,以最小化训练和测试图像之间的差距并提升LIC的能力。所提出的CIC建立了一个非线性环形方程,并通过泰勒级数展开证明,重建图像与原始图像之间的稳态误差接近于零。所提出的CIC方法具有后训练和即插即用的特性,可以基于任何现有的先进SIC方法进行构建。实验结果包括在五个公开图像压缩数据集上的率-失真曲线,显示所提出的CIC在重建能力上优于八个最先进的开源SIC算法。实验结果进一步表明,所提出的方法适用于具有暗背景、锐利边缘、高对比度、网格形状或复杂图案的样本外测试图像。

英文摘要:

Learned image compression (LIC) is currently the cutting-edge method. However, the inherent difference between testing and training images of LIC results in performance degradation to some extent. Especially for out-of-sample, out-of-distribution, or out-of-domain testing images, the performance of LIC degrades significantly. Classical LIC is a serial image compression (SIC) approach that utilizes an open-loop architecture with serial encoding and decoding units. Nevertheless, according to the principles of automatic control systems, a closed-loop architecture holds the potential to improve the dynamic and static performance of LIC. Therefore, a circular image compression (CIC) approach with closed-loop encoding and decoding elements is proposed to minimize the gap between testing and training images and upgrade the capability of LIC. The proposed CIC establishes a nonlinear loop equation and proves that steady-state error between reconstructed and original images is close to zero by Taylor series expansion. The proposed CIC method possesses the property of Post-Training and Plug-and-Play which can be built on any existing advanced SIC methods. Experimental results including rate-distortion curves on five public image compression datasets demonstrate that the proposed CIC outperforms eight competing state-of-the-art open-source SIC algorithms in reconstruction capacity. Experimental results further show that the proposed method is suitable for out-of-sample testing images with dark backgrounds, sharp edges, high contrast, grid shapes, or complex patterns.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑