提出自适应感知损失函数，提升视频压缩的视觉真实感。
On Self-Adaptive Perception Loss Function for Sequential Lossy Compression
- 基于当前帧与前一重建帧的联合分布设计感知损失
- 理论分析证明可避免误差累积，更好利用时序相关性
- 适合追求低延迟、高视觉质量的视频压缩场景
针对因果、低延迟的序列有损压缩，以均方误差（MSE）为失真度量，引入感知损失函数（PLF）提升重建图像的真实感。本文提出并分析了一种新式感知损失函数——自适应感知损失函数（PLF-SA），其考虑当前源帧与前一重建帧之间的联合分布。建立了适用于一阶马尔可夫信源的速率-失真-感知率理论模型，并对高斯模型进行了详细分析。定性表明，该方法可同时缓解误差累积问题，并更充分挖掘高质量重建间的时序相关性。通过信息论分析及在Moving MNIST和UVG数据集上的实验，验证了其优于现有方法的性能。
原文摘要 · Abstract (English)
We consider causal, low-latency, sequential lossy compression, with mean squared-error (MSE) as the distortion loss, and a perception loss function (PLF) to enhance the realism of reconstructions. As the main contribution, we propose and analyze a new PLF that considers the joint distribution between the current source frame and the previous reconstructions. We establish the theoretical rate-distortion-perception function for first-order Markov sources and analyze the Gaussian model in detail. From a qualitative perspective, the proposed metric can simultaneously avoid the error-permanence phenomenon and also better exploit the temporal correlation between high-quality reconstructions. The proposed metric is referred to as self-adaptive perception loss function (PLF-SA), as its behavior adapts to the quality of reconstructed frames. We provide a detailed comparison of the proposed perception loss function with previous approaches through both information theoretic analysis as well as experiments involving moving MNIST and UVG datasets.
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。