提出一步扩散图像超分量化方法，显著降低部署成本。
PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
- 简化模型结构，移除CLIPEncoder，聚焦UNet与VAE核心组件。
- 8位和6位量化后视觉效果接近全精度模型，性能领先现有低比特方法。
- 引入可学习边界量化与分布式校准，提升量化稳定性与收敛速度。
基于扩散的图像超分辨率模型虽表现优异，但需多步去噪，计算与存储开销大，难以在硬件设备部署。为此，我们提出一种一步扩散（OSD）图像超分的后训练量化方法PassionSR。首先，通过移除CLIPEncoder，将OSD模型简化为UNet与变分自编码器（VAE）两个核心组件；其次，提出可学习边界量化器（LBQ）与可学习等效变换（LET），优化量化过程并调整激活分布以提升量化效果；最后，设计分布式量化校准（DQC）策略，稳定量化参数训练，实现快速收敛。大量实验表明，PassionSR在8位与6位量化下，视觉质量与全精度模型相当，且显著优于当前主流低比特量化方法。代码已开源。
原文摘要 · Abstract (English)
Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps. However, even though the denoising step has been reduced to one, they require high computational costs and storage requirements, making it difficult for deployment on hardware devices. To address these issues, we propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR. First, we simplify OSD model to two core components, UNet and Variational Autoencoder (VAE) by removing the CLIPEncoder. Secondly, we propose Learnable Boundary Quantizer (LBQ) and Learnable Equivalent Transformation (LET) to optimize the quantization process and manipulate activation distributions for better quantization. Finally, we design a Distributed Quantization Calibration (DQC) strategy that stabilizes the training of quantized parameters for rapid convergence. Comprehensive experiments demonstrate that PassionSR with 8-bit and 6-bit obtains comparable visual results with full-precision model. Moreover, our PassionSR achieves significant advantages over recent leading low-bit quantization methods for image SR. Our code will be at https://github.com/libozhu03/PassionSR.
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。