Efficient Image Restoration via Latent Consistency Flow Matching

TL;DR

ELIR is a lightweight, efficient latent image restoration method that balances image quality and computational cost, enabling deployment on resource-constrained devices with competitive results.

Contribution

This paper introduces ELIR, a novel latent flow-based model that is significantly smaller and faster than existing methods for image restoration.

Findings

ELIR achieves 4x smaller model size and faster inference.

ELIR maintains competitive image restoration quality.

ELIR reduces computational costs substantially.

Abstract

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