提出低比特量化方法QuantVSR，提升真实视频超分模型的部署效率。
QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution
- 基于时空复杂度动态分配各层秩，优化量化过程。
- 在真实与合成数据集上逼近全精度模型性能，优于现有低比特方法。
- 适合需要高效部署视频超分模型的工业应用。
扩散模型在真实世界视频超分辨率（VSR）中表现优异，但其处理速度慢、资源消耗大，限制了实际应用与部署。量化为压缩VSR模型提供了可能，但因其时序特性与高保真要求，量化难度大。为此，我们提出QuantVSR，一种面向真实世界VSR的低比特量化方法。提出时空复杂度感知（STCA）机制，利用校准数据集测量每层的空间与时间复杂度，并据此为低秩全精度（FP）辅助分支分配层特定秩。随后联合优化FP与低比特分支，实现同步优化。此外，设计可学习偏置对齐（LBA）模块，降低量化偏差误差。在合成与真实世界数据集上的大量实验表明，该方法性能接近全精度模型，显著优于近期主流低比特量化方法。代码已公开：https://github.com/bowenchai/QuantVSR。
原文摘要 · Abstract (English)
Diffusion models have shown superior performance in real-world video super-resolution (VSR). However, the slow processing speeds and heavy resource consumption of diffusion models hinder their practical application and deployment. Quantization offers a potential solution for compressing the VSR model. Nevertheless, quantizing VSR models is challenging due to their temporal characteristics and high fidelity requirements. To address these issues, we propose QuantVSR, a low-bit quantization model for real-world VSR. We propose a spatio-temporal complexity aware (STCA) mechanism, where we first utilize the calibration dataset to measure both spatial and temporal complexities for each layer. Based on these statistics, we allocate layer-specific ranks to the low-rank full-precision (FP) auxiliary branch. Subsequently, we jointly refine the FP and low-bit branches to achieve simultaneous optimization. In addition, we propose a learnable bias alignment (LBA) module to reduce the biased quantization errors. Extensive experiments on synthetic and real-world datasets demonstrate that our method obtains comparable performance with the FP model and significantly outperforms recent leading low-bit quantization methods. Code is available at: https://github.com/bowenchai/QuantVSR.
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。