轻量级图像修复模型，能在低资源设备上高效运行。
Efficient Image Restoration via Latent Consistency Flow Matching
- 基于潜在空间一致性流匹配，平衡修复失真与视觉质量
- 模型体积缩小4倍，推理速度更快，支持边缘设备部署
- 在多种图像修复任务中表现优异，适合移动端应用
生成式图像修复（IR）近年来取得显著进展，但其庞大的模型规模和高计算开销限制了在边缘设备上的部署。本文提出ELIR，一种高效的潜在图像修复方法。ELIR通过潜在空间的一致性流匹配机制，有效缓解修复失真与感知质量之间的权衡，并采用轻量化架构实现高效计算。实验表明，在盲脸修复任务中，ELIR相比最先进的扩散模型和流模型，体积缩小4倍，推理速度显著提升，同时在多个图像修复任务和数据集上保持与先进方法相当的性能，实现了高质量修复与极低资源消耗的平衡。代码已开源：https://github.com/eladc-git/ELIR
原文摘要 · Abstract (English)
Recent advances in generative image restoration (IR) have demonstrated impressive results. However, these methods are hindered by their substantial size and computational demands, rendering them unsuitable for deployment on edge devices. This work introduces ELIR, an Efficient Latent Image Restoration method. ELIR addresses the distortion-perception trade-off within the latent space and produces high-quality images using a latent consistency flow-based model. In addition, ELIR introduces an efficient and lightweight architecture. Consequently, ELIR is 4$\times$ smaller and faster than state-of-the-art diffusion and flow-based approaches for blind face restoration, enabling a deployment on resource-constrained devices. Comprehensive evaluations of various image restoration tasks and datasets show that ELIR achieves competitive performance compared to state-of-the-art methods, effectively balancing distortion and perceptual quality metrics while significantly reducing model size and computational cost. The code is available at: https://github.com/eladc-git/ELIR
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。