用小波变换加速扩散GAN，实现快速高清图像超分。
A Wavelet Diffusion GAN for Image Super-Resolution
- 结合小波变换与扩散GAN，降低推理步数和计算量。
- 在CelebA-HQ上实现更快训练与推理，保持高保真输出。
- 适合对速度敏感的实时图像超分场景。
近年来，扩散模型在高保真图像生成方面成为生成对抗网络（GAN）的优越替代方案，广泛应用于文本到图像生成、图像到图像翻译及超分辨率任务。然而，其训练和推理速度慢限制了实时应用。本文提出一种基于小波变换的条件扩散GAN框架，用于单图像超分辨率（SISR）。该方法利用扩散GAN范式减少反向扩散过程所需步数，并通过离散小波变换（DWT）实现维度压缩，显著降低训练与推理时间。在CelebA-HQ数据集上的实验验证了所提方案的有效性。结果表明，该方法在保持高保真输出的同时，克服了扩散模型在时敏应用中的固有缺陷，优于现有主流方法。代码已公开于 https://www.github.com/aloilor/WaDiGAN-SR。
原文摘要 · Abstract (English)
In recent years, diffusion models have emerged as a superior alternative to generative adversarial networks (GANs) for high-fidelity image generation, with wide applications in text-to-image generation, image-to-image translation, and super-resolution. However, their real-time feasibility is hindered by slow training and inference speeds. This study addresses this challenge by proposing a wavelet-based conditional Diffusion GAN scheme for Single-Image Super-Resolution (SISR). Our approach utilizes the diffusion GAN paradigm to reduce the timesteps required by the reverse diffusion process and the Discrete Wavelet Transform (DWT) to achieve dimensionality reduction, decreasing training and inference times significantly. The results of an experimental validation on the CelebA-HQ dataset confirm the effectiveness of our proposed scheme. Our approach outperforms other state-of-the-art methodologies successfully ensuring high-fidelity output while overcoming inherent drawbacks associated with diffusion models in time-sensitive applications. The code is available at https://www.github.com/aloilor/WaDiGAN-SR
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。