UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior

Bibliographic Details
Title: UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior
Authors: Chen, I-Hsiang, Chen, Wei-Ting, Liu, Yu-Wei, Chiang, Yuan-Chun, Kuo, Sy-Yen, Yang, Ming-Hsuan
Publication Year: 2025
Collection: Computer Science
Subject Terms: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Machine Learning
More Details: Image restoration aims to recover content from inputs degraded by various factors, such as adverse weather, blur, and noise. Perceptual Image Restoration (PIR) methods improve visual quality but often do not support downstream tasks effectively. On the other hand, Task-oriented Image Restoration (TIR) methods focus on enhancing image utility for high-level vision tasks, sometimes compromising visual quality. This paper introduces UniRestore, a unified image restoration model that bridges the gap between PIR and TIR by using a diffusion prior. The diffusion prior is designed to generate images that align with human visual quality preferences, but these images are often unsuitable for TIR scenarios. To solve this limitation, UniRestore utilizes encoder features from an autoencoder to adapt the diffusion prior to specific tasks. We propose a Complementary Feature Restoration Module (CFRM) to reconstruct degraded encoder features and a Task Feature Adapter (TFA) module to facilitate adaptive feature fusion in the decoder. This design allows UniRestore to optimize images for both human perception and downstream task requirements, addressing discrepancies between visual quality and functional needs. Integrating these modules also enhances UniRestore's adapability and efficiency across diverse tasks. Extensive expertments demonstrate the superior performance of UniRestore in both PIR and TIR scenarios.
Comment: 11 pages, 6 figures
Document Type: Working Paper
Access URL: http://arxiv.org/abs/2501.13134
Accession Number: edsarx.2501.13134
Database: arXiv
More Details
Description not available.