轻量级适配器让扩散模型更好修复真实图像。
Diffusion Restoration Adapter for Real-World Image Restoration
- 用轻量适配器激活预训练扩散模型的生成能力
- 在真实图像修复任务中达到逼真效果
- 适用于去噪UNet和DiT，参数少效率高
扩散模型展现出强大的图像生成能力，能有效拟合复杂的图像分布，可作为图像修复的强大先验。现有方法常借助ControlNet等技术，利用先验从低质量图像生成高质量图像，但ControlNet通常需复制原网络大量结构，导致参数量随先验规模显著增加。本文提出一种轻量级适配器，充分利用预训练先验的生成能力，实现照片级真实的图像修复。该适配器可适配去噪UNet与DiT架构，性能优异。
原文摘要 · Abstract (English)
Diffusion models have demonstrated their powerful image generation capabilities, effectively fitting highly complex image distributions. These models can serve as strong priors for image restoration. Existing methods often utilize techniques like ControlNet to sample high quality images with low quality images from these priors. However, ControlNet typically involves copying a large part of the original network, resulting in a significantly large number of parameters as the prior scales up. In this paper, we propose a relatively lightweight Adapter that leverages the powerful generative capabilities of pretrained priors to achieve photo-realistic image restoration. The Adapters can be adapt to both denoising UNet and DiT, and performs excellent.
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。