QuantDemoire：面向图像去摩尔纹的离群值感知量化
QuantDemoire: Quantization with Outlier Aware for Image Demoiréing
AI总结：
针对现有量化方法直接用于图像去摩尔纹模型性能下降的问题，提出含离群值感知量化器和频率感知校准策略的QuantDemoire训练后量化框架，在大幅压缩模型的同时保持去摩尔纹质量，性能优于现有方法。
摘要：
去摩尔纹旨在消除图像中常见的摩尔纹伪影。尽管近期基于深度学习的方法已取得可观成效，但它们通常需要大量计算资源，限制了在边缘设备上的部署。模型量化提供了一种极具吸引力的解决方案，然而直接将现有量化方法应用于去摩尔纹模型会导致严重的性能下降，主要原因在于分布离群值以及平滑区域的表征能力减弱。为解决这些问题，我们提出QuantDemoire——一种专为去摩尔纹任务定制的训练后量化框架，它包含两个核心组件。第一，我们提出一种离群值感知量化器以降低离群值带来的误差：它采用基于采样的范围估计来减少激活离群值，同时以可忽略的开销将少量极端权重保留为FP16格式。第二，我们设计了一种频率感知校准策略：在微调过程中重点关注低频和中频分量，缓解低比特量化引发的条带伪影。大量实验验证，我们的QuantDemoire在保持图像质量的同时大幅减少了参数量和计算量；此外在W4A4配置下，其性能优于现有量化方法4 dB以上。代码已发布于：https://github.com/zhengchen1999/QuantDemoire。
英文摘要：
Demoiréing aims to remove moiré artifacts that often occur in images. While recent deep learning-based methods have achieved promising results, they typically require substantial computational resources, limiting their deployment on edge devices. Model quantization offers a compelling solution. However, directly applying existing quantization methods to demoiréing models introduces severe performance degradation. The main reasons are distribution outliers and weakened representations in smooth regions. To address these issues, we propose QuantDemoire, a post-training quantization framework tailored to demoiréing. It contains two key components. **First}, we introduce an outlier-aware quantizer to reduce errors from outliers. It uses sampling-based range estimation to reduce activation outliers, and keeps a few extreme weights in FP16 with negligible cost. **Second**, we design a frequency-aware calibration strategy. It emphasizes low- and mid-frequency components during fine-tuning, which mitigates banding artifacts caused by low-bit quantization. Extensive experiments validate that our QuantDemoire achieves large reductions in parameters and computation while maintaining quality. Meanwhile, it outperforms existing quantization methods by over **4 dB** on W4A4. Code is released at: https://github.com/zhengchen1999/QuantDemoire.
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。
