DA2Diff: Exploring Degradation-aware Adaptive Diffusion Priors for All-in-One Weather Restoration

• URL: http://arxiv.org/abs/2504.05135v1
• Date: Mon, 07 Apr 2025 14:38:57 GMT
• Title: DA2Diff: Exploring Degradation-aware Adaptive Diffusion Priors for All-in-One Weather Restoration
• Authors: Jiamei Xiong, Xuefeng Yan, Yongzhen Wang, Wei Zhao, Xiao-Ping Zhang, Mingqiang Wei,
• Abstract summary: We propose an innovative diffusion paradigm with degradation-aware adaptive priors for all-in-one weather restoration, termed DA2Diff.<n>We deploy a set of learnable prompts to capture degradation-aware representations by the prompt-image similarity constraints in the CLIP space.<n>We propose a dynamic expert selection modulator that employs a dynamic weather-aware router to flexibly dispatch varying numbers of restoration experts for each weather-distorted image.
• Score: 32.16602874389847
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image restoration under adverse weather conditions is a critical task for many vision-based applications. Recent all-in-one frameworks that handle multiple weather degradations within a unified model have shown potential. However, the diversity of degradation patterns across different weather conditions, as well as the complex and varied nature of real-world degradations, pose significant challenges for multiple weather removal. To address these challenges, we propose an innovative diffusion paradigm with degradation-aware adaptive priors for all-in-one weather restoration, termed DA2Diff. It is a new exploration that applies CLIP to perceive degradation-aware properties for better multi-weather restoration. Specifically, we deploy a set of learnable prompts to capture degradation-aware representations by the prompt-image similarity constraints in the CLIP space. By aligning the snowy/hazy/rainy images with snow/haze/rain prompts, each prompt contributes to different weather degradation characteristics. The learned prompts are then integrated into the diffusion model via the designed weather specific prompt guidance module, making it possible to restore multiple weather types. To further improve the adaptiveness to complex weather degradations, we propose a dynamic expert selection modulator that employs a dynamic weather-aware router to flexibly dispatch varying numbers of restoration experts for each weather-distorted image, allowing the diffusion model to restore diverse degradations adaptively. Experimental results substantiate the favorable performance of DA2Diff over state-of-the-arts in quantitative and qualitative evaluation. Source code will be available after acceptance.

Related papers

• Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal [19.896064731182985]
  Universal adverse weather removal (UAWR) seeks to address various weather degradations within a unified framework. Recent methods are inspired by prompt learning using pre-trained vision-language models (e.g., CLIP) We propose CyclicPrompt, an innovative cyclic prompt approach designed to enhance the effectiveness, adaptability, and generalizability of UAWR.
  arXiv  Detail & Related papers  (2025-03-12T03:03:06Z)
• Removing Multiple Hybrid Adverse Weather in Video via a Unified Model [6.868658821057831]
  We propose a novel unified model, dubbed UniWRV, to remove multiple heterogeneous video weather degradations in an all-in-one fashion. Our UniWRV exhibits robust and superior adaptation capability in multiple heterogeneous degradations learning scenarios.
  arXiv  Detail & Related papers  (2025-03-08T13:01:22Z)
• MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers [44.600209414790854]
  Restoring images captured under adverse weather conditions is a fundamental task for many computer vision applications. We propose a multi-weather Transformer, or MWFormer, that aims to solve multiple weather-induced degradations using a single architecture. We show that MWFormer achieves significant performance improvements compared to existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-26T08:47:39Z)
• Multiple weather images restoration using the task transformer and adaptive mixup strategy [14.986500375481546]
  We introduce a novel multi-task severe weather removal model that can effectively handle complex weather conditions in an adaptive manner. Our model incorporates a weather task sequence generator, enabling the self-attention mechanism to selectively focus on features specific to different weather types. Our proposed model has achieved state-of-the-art performance on the publicly available dataset.
  arXiv  Detail & Related papers  (2024-09-05T04:55:40Z)
• Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure [92.8834309803903]
  In real-world applications, image degeneration caused by adverse weather is always complex and changes with different weather conditions from days and seasons. We develop a novel continual learning framework with effective knowledge replay (KR) on a unified network structure. It considers the characteristics of the image restoration task with multiple degenerations in continual learning, and the knowledge for different degenerations can be shared and accumulated.
  arXiv  Detail & Related papers  (2024-03-12T03:50:57Z)
• Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removal [8.58670633761819]
  All-in-one adverse weather removal is an emerging topic on image restoration, which aims to restore multiple weather degradations in an unified model. We propose a degradation type and severity aware model, called UtilityIR, for blind all-in-one bad weather image restoration.
  arXiv  Detail & Related papers  (2023-10-27T17:29:55Z)
• Cross-Consistent Deep Unfolding Network for Adaptive All-In-One Video Restoration [78.14941737723501]
  We propose a Cross-consistent Deep Unfolding Network (CDUN) for All-In-One VR. By orchestrating two cascading procedures, CDUN achieves adaptive processing for diverse degradations. In addition, we introduce a window-based inter-frame fusion strategy to utilize information from more adjacent frames.
  arXiv  Detail & Related papers  (2023-09-04T14:18:00Z)
• MetaWeather: Few-Shot Weather-Degraded Image Restoration [17.63266150036311]
  We introduce MetaWeather, a universal approach that can handle diverse and novel weather conditions with a single unified model. We show that MetaWeather can adapt to unseen weather conditions, significantly outperforming state-of-the-art multi-weather image restoration methods.
  arXiv  Detail & Related papers  (2023-08-28T06:25:40Z)
• Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removal [97.53040662243768]
  We propose a CLIP embedding module to make the network handle different weather conditions adaptively. This module integrates the sample specific weather prior extracted by CLIP image encoder together with the distribution specific information learned by a set of parameters.
  arXiv  Detail & Related papers  (2023-06-15T10:06:13Z)
• Counting Crowds in Bad Weather [68.50690406143173]
  We propose a method for robust crowd counting in adverse weather scenarios. Our model learns effective features and adaptive queries to account for large appearance variations. Experimental results show that the proposed algorithm is effective in counting crowds under different weather types on benchmark datasets.
  arXiv  Detail & Related papers  (2023-06-02T00:00:09Z)
• Rethinking Real-world Image Deraining via An Unpaired Degradation-Conditioned Diffusion Model [51.49854435403139]
  We propose RainDiff, the first real-world image deraining paradigm based on diffusion models. We introduce a stable and non-adversarial unpaired cycle-consistent architecture that can be trained, end-to-end, with only unpaired data for supervision. We also propose a degradation-conditioned diffusion model that refines the desired output via a diffusive generative process conditioned by learned priors of multiple rain degradations.
  arXiv  Detail & Related papers  (2023-01-23T13:34:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.