用于物理感知单幅图像去雾的课程对比正则化
Curricular Contrastive Regularization for Physics-aware Single Image Dehazing
AI总结：
针对单幅图像去雾中对比样本非共识、约束不足及物理可解释性弱的问题，提出课程对比正则化与大气散射模型驱动的 C2PNet，在 SOTS 室内外基准上显著提升 PSNR。
摘要：
考虑到单幅图像去雾问题的病态性质，研究者已发展出对比正则化方法，通过引入负样本图像的信息作为下界。然而，对比样本并非共识性的：负样本通常在表示上远离清晰（即正样本）图像，导致解空间仍然约束不足。此外，深度去雾模型在雾生成过程的物理机理方面，其可解释性尚未得到充分探索。本文提出一种新颖的课程对比正则化，旨在构建共识性对比空间，而非非共识性空间。我们的负样本能够提供更优的下界约束，可由以下两部分组合而成：1）有雾图像；2）其他现有方法对应的复原结果。此外，由于清晰图像与负样本的嵌入之间存在不同的相似度，多个组成部分的学习难度本质上是不平衡的。为解决该问题，我们定制了一种课程学习策略，对不同负样本的重要性进行重新加权。另外，为提升特征空间中的可解释性，我们依据大气散射模型构建了一个物理感知双分支单元。借助该单元以及课程对比正则化，我们建立了名为 C2PNet 的去雾网络。大量实验表明，C2PNet 显著优于最先进方法，在 SOTS-indoor 和 SOTS-outdoor 数据集上分别取得高达 3.94dB 和 1.50dB 的 PSNR 提升。
英文摘要：
Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are nonconsensual, as the negatives are usually represented distantly from the clear (i.e., positive) image, leaving the solution space still under-constricted. Moreover, the interpretability of deep dehazing models is underexplored towards the physics of the hazing process. In this paper, we propose a novel curricular contrastive regularization targeted at a consensual contrastive space as opposed to a non-consensual one. Our negatives, which provide better lower-bound constraints, can be assembled from 1) the hazy image, and 2) corresponding restorations by other existing methods. Further, due to the different similarities between the embeddings of the clear image and negatives, the learning difficulty of the multiple components is intrinsically imbalanced. To tackle this issue, we customize a curriculum learning strategy to reweight the importance of different negatives. In addition, to improve the interpretability in the feature space, we build a physics-aware dual-branch unit according to the atmospheric scattering model. With the unit, as well as curricular contrastive regularization, we establish our dehazing network, named C2PNet. Extensive experiments demonstrate that our C2PNet significantly outperforms state-of-the-art methods, with extreme PSNR boosts of 3.94dB and 1.50dB, respectively, on SOTS-indoor and SOTS-outdoor datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
