QARV：面向有损图像压缩的量化感知 ResNet VAE
QARV: Quantization-Aware ResNet VAE for Lossy Image Compression
AI总结：
本文提出量化感知 ResNet VAE（QARV）用于有损图像压缩，通过分层 VAE 架构、测试时量化与量化感知训练，实现可变码率压缩、高速解码和优于基线的率失真性能。
摘要：
本文研究有损图像压缩问题，这是图像处理与信息论中的一个基础问题，涉及众多实际应用。我们首先回顾变分自编码器（VAEs）框架，这是一类强大的生成式概率模型，与有损压缩有着深刻联系。基于 VAEs，我们提出一种新的有损图像压缩方案，命名为量化感知 ResNet VAE（QARV）。该方法采用分层 VAE 架构，并结合测试时量化与量化感知训练，没有这些设计就无法实现高效的熵编码。此外，我们专门针对快速解码设计了 QARV 的神经网络架构，并提出一种用于可变码率压缩的自适应归一化操作。大量实验结果表明，QARV 实现了可变码率压缩、高速解码，并且相比现有基线方法具有更好的率失真性能。本文方法的代码已在 https://github.com/duanzhiihao/lossy-vae 公开。
英文摘要：
This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications. We start by reviewing the framework of variational autoencoders (VAEs), a powerful class of generative probabilistic models that has a deep connection to lossy compression. Based on VAEs, we develop a novel scheme for lossy image compression, which we name quantization-aware ResNet VAE (QARV). Our method incorporates a hierarchical VAE architecture integrated with test-time quantization and quantization-aware training, without which efficient entropy coding would not be possible. In addition, we design the neural network architecture of QARV specifically for fast decoding and propose an adaptive normalization operation for variable-rate compression. Extensive experiments are conducted, and results show that QARV achieves variable-rate compression, high-speed decoding, and a better rate-distortion performance than existing baseline methods. The code of our method is publicly accessible at https://github.com/duanzhiihao/lossy-vae
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。
