CoA: Towards Real Image Dehazing via Compression-and-Adaptation

• URL: http://arxiv.org/abs/2504.05590v1
• Date: Tue, 08 Apr 2025 00:56:33 GMT
• Title: CoA: Towards Real Image Dehazing via Compression-and-Adaptation
• Authors: Long Ma, Yuxin Feng, Yan Zhang, Jinyuan Liu, Weimin Wang, Guang-Yong Chen, Chengpei Xu, Zhuo Su,
• Abstract summary: Learning-based image dehazing algorithms have shown remarkable success in synthetic domains.<n>Real image dehazing is still in suspense due to computational resource constraints and the diversity of real-world scenes.<n>This work proposes a Compression-and-Adaptation (CoA) computational flow to tackle these challenges.
• Score: 25.615037000420834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning-based image dehazing algorithms have shown remarkable success in synthetic domains. However, real image dehazing is still in suspense due to computational resource constraints and the diversity of real-world scenes. Therefore, there is an urgent need for an algorithm that excels in both efficiency and adaptability to address real image dehazing effectively. This work proposes a Compression-and-Adaptation (CoA) computational flow to tackle these challenges from a divide-and-conquer perspective. First, model compression is performed in the synthetic domain to develop a compact dehazing parameter space, satisfying efficiency demands. Then, a bilevel adaptation in the real domain is introduced to be fearless in unknown real environments by aggregating the synthetic dehazing capabilities during the learning process. Leveraging a succinct design free from additional constraints, our CoA exhibits domain-irrelevant stability and model-agnostic flexibility, effectively bridging the model chasm between synthetic and real domains to further improve its practical utility. Extensive evaluations and analyses underscore the approach's superiority and effectiveness. The code is publicly available at https://github.com/fyxnl/COA.

Related papers

• Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation [75.58269386927076]
  Autoregressive (AR) models are often dismissed as impractical due to prohibitive computational cost.<n>This work re-thinks this paradigm, introducing a framework built on hierarchical parallelism and progressive adaptation.<n> Experiments on diverse datasets (natural, satellite, medical) validate that our method achieves new state-of-the-art compression.
  arXiv  Detail & Related papers  (2025-11-14T06:27:58Z)
• Bridging the Synthetic-Real Gap: Supervised Domain Adaptation for Robust Spacecraft 6-DoF Pose Estimation [13.83897333268682]
  Spacecraft Pose Estimation is a fundamental capability for autonomous space operations such as rendezvous, docking, and in-orbit docking.<n>Existing domain adaptation approaches aim to mitigate this issue but often underperform when a modest number of labeled target samples are available.<n>We propose the first Supervised Domain Adaptation (SDA) framework tailored for SPE keypoint regression.
  arXiv  Detail & Related papers  (2025-09-17T08:03:05Z)
• IntrinsicReal: Adapting IntrinsicAnything from Synthetic to Real Objects [26.907664563000257]
  Estimating albedo (a.k.a., intrinsic image decomposition) from single RGB images captured in real-world environments presents a significant challenge.<n>We propose IntrinsicReal, a novel domain adaptation framework that bridges the domain gap for real-world intrinsic image decomposition.<n>Our IntrinsicReal significantly outperforms existing methods, achieving state-of-the-art results for albedo estimation on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2025-08-31T10:15:31Z)
• Real-World Remote Sensing Image Dehazing: Benchmark and Baseline [19.747354924759104]
  The scarcity of real-world remote sensing hazy image pairs has compelled existing methods to rely primarily on synthetic datasets.<n>We introduce Real-World Remote Sensing Hazy Image dataset (RRSHID), the first large-scale dataset featuring real-world hazy and dehazed image pairs.<n>Based on this, we propose MCAF-Net, a novel framework tailored for real-world RSID.
  arXiv  Detail & Related papers  (2025-03-23T07:15:46Z)
• MambaIC: State Space Models for High-Performance Learned Image Compression [53.991726013454695]
  A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields.<n>Inspired by the effectiveness of state space models (SSMs) in capturing long-range dependencies, we leverage SSMs to address computational inefficiency in existing methods.<n>We propose an enhanced image compression approach through refined context modeling, which we term MambaIC.
  arXiv  Detail & Related papers  (2025-03-16T11:32:34Z)
• Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration [64.84134880709625]
  We show that it is possible to perform domain adaptation via the noise space using diffusion models.<n>In particular, by leveraging the unique property of how auxiliary conditional inputs influence the multi-step denoising process, we derive a meaningful diffusion loss.<n>We present crucial strategies such as channel-shuffling layer and residual-swapping contrastive learning in the diffusion model.
  arXiv  Detail & Related papers  (2024-06-26T17:40:30Z)
• Efficient Degradation-aware Any Image Restoration [83.92870105933679]
  We propose textitDaAIR, an efficient All-in-One image restorer employing a Degradation-aware Learner (DaLe) in the low-rank regime. By dynamically allocating model capacity to input degradations, we realize an efficient restorer integrating holistic and specific learning.
  arXiv  Detail & Related papers  (2024-05-24T11:53:27Z)
• Efficient Imitation Learning with Conservative World Models [54.52140201148341]
  We tackle the problem of policy learning from expert demonstrations without a reward function. We re-frame imitation learning as a fine-tuning problem, rather than a pure reinforcement learning one.
  arXiv  Detail & Related papers  (2024-05-21T20:53:18Z)
• Representing Domain-Mixing Optical Degradation for Real-World Computational Aberration Correction via Vector Quantization [17.08845012632751]
  Existing learning-based Computational Aberration Correction (CAC) methods are confronted with the intricate and multifaceted synthetic-to-real domain gap. We deliver a novel insight into real-world CAC from the perspective of Unsupervised Domain Adaptation (UDA) We propose a novel Quantized Domain-Mixing Representation (QDMR) framework as a potent solution to the issue.
  arXiv  Detail & Related papers  (2024-03-15T04:35:25Z)
• RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors [14.432465539590481]
  Existing dehazing approaches struggle to process real-world hazy images owing to the lack of paired real data and robust priors. We present a new paradigm for real image dehazing from the perspectives of synthesizing more realistic hazy data.
  arXiv  Detail & Related papers  (2023-04-08T12:12:24Z)
• Toward Fast, Flexible, and Robust Low-Light Image Enhancement [87.27326390675155]
  We develop a new Self-Calibrated Illumination (SCI) learning framework for fast, flexible, and robust brightening images in real-world low-light scenarios. Considering the computational burden of the cascaded pattern, we construct the self-calibrated module which realizes the convergence between results of each stage. We make comprehensive explorations to SCI's inherent properties including operation-insensitive adaptability and model-irrelevant generality.
  arXiv  Detail & Related papers  (2022-04-21T14:40:32Z)
• Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution [28.00231586840797]
  Real-world image super-resolution (Real-ISR) is a challenging task due to the unknown complex degradation of real-world images. Recent research on Real-ISR has achieved significant progress by modeling the image degradation space. We propose an efficient degradation-adaptive super-resolution (DASR) network, whose parameters are adaptively specified by estimating the degradation of each input image.
  arXiv  Detail & Related papers  (2022-03-27T05:59:13Z)
• Domain Adaptation for Underwater Image Enhancement [51.71570701102219]
  We propose a novel Two-phase Underwater Domain Adaptation network (TUDA) to minimize the inter-domain and intra-domain gap. In the first phase, a new dual-alignment network is designed, including a translation part for enhancing realism of input images, followed by an enhancement part. In the second phase, we perform an easy-hard classification of real data according to the assessed quality of enhanced images, where a rank-based underwater quality assessment method is embedded.
  arXiv  Detail & Related papers  (2021-08-22T06:38:19Z)
• Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation [16.153683223016973]
  We develop an attention module that learns to identify and remove difficult out-of-domain regions in real images. Visualizing the removed regions provides interpretable insights into the synthetic-real domain gap.
  arXiv  Detail & Related papers  (2020-02-27T14:28:56Z)

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.