图像复原
计算机科学
任务(项目管理)
感知
图像(数学)
扩散
计算机视觉
人工智能
图像处理
心理学
工程类
物理
系统工程
热力学
神经科学
作者
I-Hsiang Chen,Wei‐Ting Chen,Yuwei Liu,Yuan-Chun Chiang,Sy‐Yen Kuo,Ming–Hsuan Yang
出处
期刊:Proceedings
[Institute of Electrical and Electronics Engineers]
日期:2025-06-10
卷期号:: 17969-17979
被引量:72
标识
DOI:10.1109/cvpr52734.2025.01674
摘要
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 adaptability and efficiency across diverse tasks. Extensive experiments demonstrate the superior performance of UniRestore in both PIR and TIR scenarios.
科研通智能强力驱动
Strongly Powered by AbleSci AI