首页|Learning depth-aware decomposition for single image dehazing
Learning depth-aware decomposition for single image dehazing
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Elsevier
Image dehazing under deficient data is an ill-posed and challenging problem。 Most existing methods tackle this task by developing either CycleGAN-based hazy-to-clean translation or physical-based haze decomposition。 However， geometric structure is often not effectively incorporated in their straightforward hazy-clean projection framework， which might incur inaccurate estimation in distant areas。 In this paper， we rethink the image dehazing task and propose a depth-aware perception framework， DehazeDP， for robust haze decomposition on deficient data。 Our DehazeDP is insthe pired by Diffusion Probabilistic Model to form an end-to-end training pipeline that seamlessly ines the hazy image generation with haze disentanglement。 Specifically， in the forward phase， the haze is added to a clean image step-by-step according to the depth distribution。 Then， in the reverse phase， a unified U-Net is used to predict the haze and recover the clean image progressively。 Extensive experiments on public datasets demonstrate that the proposed DehazeDP performs favorably against state-of-the-art approaches。
Single image dehazingDenoising diffusion probabilistic modelsSelf-supervised learning
Yumeng Kang、Lu Zhang、Ping Hu、Yu Liu、Huchuan Lu、You He
展开 >
Shenzhen International Graduate School Tsinghua University, Shenzhen, China
NETL
NSTL
Elsevier
