arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.04286eess.IVcs.CV
收藏

无干净参考的去噪器的改进与学习

Enhancing and Learning Denoiser without Clean Reference

The Hong Kong Polytechnic University(香港理工大学)

Rui Zhao, Daniel P. K. Lun, Kin-Man Lam

摘要:

最近的研究基于学习的图像去噪取得了良好的性能在各种降噪任务。这些深度去噪器中的大多数都是在干净参考的监督下训练的,或者是在合成噪声的无监督下训练的。当面对真实照片时,合成噪声的假设导致泛化能力差。为了解决这个问题,我们提出了一种新的深度图像去噪方法,将降噪任务视为噪声转移任务的特殊情况。学习噪声迁移使网络能够通过观察污染样本来获得去噪能力。真实世界去噪基准测试的结果表明,我们提出的方法在去除现实噪声方面取得了令人满意的性能,使其成为实际降噪问题的潜在解决方案。

英文摘要:

Recent studies on learning-based image denoising have achieved promising performance on various noise reduction tasks. Most of these deep denoisers are trained either under the supervision of clean references, or unsupervised on synthetic noise. The assumption with the synthetic noise leads to poor generalization when facing real photographs. To address this issue, we propose a novel deep image-denoising method by regarding the noise reduction task as a special case of the noise transference task. Learning noise transference enables the network to acquire the denoising ability by observing the corrupted samples. The results on real-world denoising benchmarks demonstrate that our proposed method achieves promising performance on removing realistic noises, making it a potential solution to practical noise reduction problems.

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。

↑