改进过拟合神经编码中的上采样，降低参数量并提升压缩效率。
Upsampling Improvement for Overfitted Neural Coding
- 提出新型上采样结构，减少网络参数和计算复杂度。
- 在Cool-Chic框架下实现4.7%的码率降低。
- 适合追求低复杂度高效率图像压缩的研究者与开发者。
基于自编码器和过拟合表征的神经图像压缩依赖于对编码信号的紧凑潜变量表示，该表示使用低分辨率特征图。解码过程中，这些潜变量通过堆叠卷积滤波器与非线性单元进行上采样和滤波以恢复图像。因此，上采样过程在神经编码设计中至关重要，尤其在过拟合编码器中，网络参数（包括上采样滤波器）构成表示的一部分。本文针对上采样过程提出改进，以降低其复杂度并减少参数数量。所提方法在Cool-Chic过拟合图像编码框架中验证，实现了4.7%的码率降低。代码已公开。
原文摘要 · Abstract (English)
Neural image compression, based on auto-encoders and overfitted representations, relies on a latent representation of the coded signal. This representation needs to be compact and uses low resolution feature maps. In the decoding process, those latents are upsampled and filtered using stacks of convolution filters and non linear elements to recover the decoded image. Therefore, the upsampling process is crucial in the design of a neural coding scheme and is of particular importance for overfitted codecs where the network parameters, including the upsampling filters, are part of the representation. This paper addresses the improvement of the upsampling process in order to reduce its complexity and limit the number of parameters. A new upsampling structure is presented whose improvements are illustrated within the Cool-Chic overfitted image coding framework. The proposed approach offers a rate reduction of 4.7%. The code is provided.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。