cs.CVOct 5, 2025

QuantDemoire: Quantization with Outlier Aware for Image Demoiréing

Authors: Zheng Chen, Kewei Zhang, Xiaoyang Liu, Weihang Zhang, Mengfan Wang, Yifan Fu, Yulun Zhang

Organizations: Shanghai Jiao Tong University · Central Media Technology Institute, Huawei

Abstract

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. 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. We implement a CUDA kernel for the mixed-precision branch and achieve a 2.3×\times end-to-end speedup on an RTX 4090 GPU. Code is released at: https://github.com/zhengchen1999/QuantDemoire.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Dual-Scale Condition-Shift Editing for Robust Real-World Image Demoiréing

    Oct 19, 2026Shiyang Zhou, Haijin Zeng, Congpei Qiu +6Image RestorationImage Corruption Robustness

  2. Decoder-Free Distillation for Quantized Image Restoration

    Mar 10, 2026S. M. A. Sharif, Abdur Rehman, Seongwan Kim +1Image RestorationQuantization-Aware Distillation