双向去雾与生雾模型，仅15步即可高效转换
Residual-based Efficient Bidirectional Diffusion Model for Image Dehazing and Haze Generation
- 用双马尔可夫链处理残差，实现去雾与生雾平滑切换
- 在合成与真实数据集上均达顶尖或相当性能
- 小数据下仍高效，适合资源受限场景使用
现有深度去雾方法仅能去除雾霾，无法在有雾与无雾图像间双向转换。为此，我们提出基于残差的高效双向扩散模型（RBDM），可建模去雾与生雾的条件分布。首先，设计双马尔可夫链，有效传递残差，实现双向平滑过渡；其次，模型在各时间步对有雾与无雾图像进行扰动，并预测扰动数据中的噪声，同步学习两种条件分布；最后，为提升小数据表现并降低计算成本，采用在图像块上学习的统一得分函数，而非整图。实验表明，该模型仅需15次采样步骤，即可实现无雾与有雾图像间的尺寸无关双向转换，在合成与真实世界数据集上均达到或超过当前最优性能。
原文摘要 · Abstract (English)
Current deep dehazing methods only focus on removing haze from hazy images, lacking the capability to translate between hazy and haze-free images. To address this issue, we propose a residual-based efficient bidirectional diffusion model (RBDM) that can model the conditional distributions for both dehazing and haze generation. Firstly, we devise dual Markov chains that can effectively shift the residuals and facilitate bidirectional smooth transitions between them. Secondly, the RBDM perturbs the hazy and haze-free images at individual timesteps and predicts the noise in the perturbed data to simultaneously learn the conditional distributions. Finally, to enhance performance on relatively small datasets and reduce computational costs, our method introduces a unified score function learned on image patches instead of entire images. Our RBDM successfully implements size-agnostic bidirectional transitions between haze-free and hazy images with only 15 sampling steps. Extensive experiments demonstrate that the proposed method achieves superior or at least comparable performance to state-of-the-art methods on both synthetic and real-world datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。