Transfer CLIP for Generalizable Image Denoising

TL;DR

This paper introduces a novel image denoising approach that leverages CLIP's dense features to improve robustness against out-of-distribution noise, outperforming existing methods across various noise types.

Contribution

The paper uncovers CLIP's dense features' properties for denoising and proposes a new asymmetrical encoder-decoder network with progressive feature augmentation for better generalization.

Findings

Superior performance on diverse OOD noise datasets

Effective use of CLIP's dense features for denoising

Enhanced robustness with progressive feature augmentation

Abstract

Image denoising is a fundamental task in computer vision. While prevailing deep learning-based supervised and self-supervised methods have excelled in eliminating in-distribution noise, their susceptibility to out-of-distribution (OOD) noise remains a significant challenge. The recent emergence of contrastive language-image pre-training (CLIP) model has showcased exceptional capabilities in open-world image recognition and segmentation. Yet, the potential for leveraging CLIP to enhance the robustness of low-level tasks remains largely unexplored. This paper uncovers that certain dense features extracted from the frozen ResNet image encoder of CLIP exhibit distortion-invariant and content-related properties, which are highly desirable for generalizable denoising. Leveraging these properties, we devise an asymmetrical encoder-decoder denoising network, which incorporates dense features including the noisy image and its multi-scale features from the frozen ResNet encoder of CLIP into a learnable image decoder to achieve generalizable denoising. The progressive feature augmentation strategy is further proposed to mitigate feature overfitting and improve the robustness of the learnable decoder. Extensive experiments and comparisons conducted across diverse OOD noises, including synthetic noise, real-world sRGB noise, and low-dose CT image noise, demonstrate the superior generalization ability of our method.