Although there are many excellent solutions in image restoration, the fact
that they are specifically designed for a single image restoration task may
prevent them from being state-of-the-art (SOTA) in other types of image
restoration tasks. While some approaches require considering multiple image
restoration tasks, they are still not sufficient for the requirements of the
real world and may suffer from the task confusion issue. In this work, we focus
on designing a unified and effective solution for multiple image restoration
tasks including deraining, desnowing, defogging, deblurring, denoising, and
low-light enhancement. Based on the above purpose, we propose a Transformer
network Restorer with U-Net architecture. In order to effectively deal with
degraded information in multiple image restoration tasks, we need a more
comprehensive attention mechanism. Thus, we design all-axis attention (AAA)
through stereo embedding and 3D convolution, which can simultaneously model the
long-range dependencies in both spatial and channel dimensions, capturing
potential correlations among all axis. Moreover, we propose a Restorer based on
textual prompts. Compared to previous methods that employ learnable queries,
textual prompts bring explicit task priors to solve the task confusion issue
arising from learnable queries and introduce interactivity. Based on these
designs, Restorer demonstrates SOTA or comparable performance in multiple image
restoration tasks compared to universal image restoration frameworks and
methods specifically designed for these individual tasks. Meanwhile, Restorer
is faster during inference. The above results along with the real-world test
results show that Restorer has the potential to serve as a backbone for
multiple real-world image restoration tasks.

通过 Transformer 网络 Restorer，我们设计了一种综合有效的解决方案，能够在去雨、去雪、去雾、去模糊等多种图像修复任务中展现国际领先或可比较的性能，并且在推理时速度更快。

Restorer: 使用一组参数解决多个图像恢复任务

Restorer: Solving Multiple Image Restoration Tasks with One Set of  Parameters

We investigated domain adaptive semantic segmentation in foggy weather
scenarios, which aims to enhance the utilization of unlabeled foggy data and
improve the model's adaptability to foggy conditions. Current methods rely on
clear images as references, jointly learning defogging and segmentation for
foggy images. Despite making some progress, there are still two main drawbacks:
(1) the coupling of segmentation and defogging feature representations,
resulting in a decrease in semantic representation capability, and (2) the
failure to leverage real fog priors in unlabeled foggy data, leading to
insufficient model generalization ability. To address these issues, we propose
a novel training framework, Decouple Defogging and Semantic learning, called
D2SL, aiming to alleviate the adverse impact of defogging tasks on the final
segmentation task. In this framework, we introduce a domain-consistent transfer
strategy to establish a connection between defogging and segmentation tasks.
Furthermore, we design a real fog transfer strategy to improve defogging
effects by fully leveraging the fog priors from real foggy images. Our approach
enhances the semantic representations required for segmentation during the
defogging learning process and maximizes the representation capability of fog
invariance by effectively utilizing real fog data. Comprehensive experiments
validate the effectiveness of the proposed method.

提出 D2SL 框架，通过解耦雾化和语义学习任务，引入领域一致性转换策略和真实雾化转换策略，提高模型在雾化条件下的自适应能力和语义表达能力。