arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1803.04477cs.CV
收藏

投影校正:用生成对抗网络去噪图像

Correction by Projection: Denoising Images with Generative Adversarial Networks

UC San Diego(加州大学圣地亚哥分校)

Subarna Tripathi, Zachary C. Lipton, Truong Q. Nguyen

摘要:

生成对抗网络(GANs)将低维潜在向量转换为视觉上合理的图像。如果真实数据集只包含干净的图像,那么表面上,GAN学习的流形应该只包含干净的图像。在本文中,我们提出了去噪损坏的图像通过找到最近的点上的GAN流形,恢复潜向量,通过最小化图像空间中的距离。我们首先证明,给定一个真正位于GAN流形上的图像的损坏版本,我们可以近似地恢复潜向量并对图像进行降噪,与BM 3D相比,获得了更高的质量。接下来,我们证明了从噪声图像中恢复的潜在向量表现出一致的偏差。通过在投影回图像空间之前减去此偏差,我们进一步改善了去噪结果。最后,即使对于看不见的图像,我们的方法在去噪方面也比BM3D表现得更好。值得注意的是,我们的方法的基本版本(没有偏差校正)不需要关于噪声方差的先验知识。为了实现尽可能高的去噪质量,性能最好的基于信号处理的方法,如BM 3D,需要对模糊核进行估计。

英文摘要:

Generative adversarial networks (GANs) transform low-dimensional latent vectors into visually plausible images. If the real dataset contains only clean images, then ostensibly, the manifold learned by the GAN should contain only clean images. In this paper, we propose to denoise corrupted images by finding the nearest point on the GAN manifold, recovering latent vectors by minimizing distances in image space. We first demonstrate that given a corrupted version of an image that truly lies on the GAN manifold, we can approximately recover the latent vector and denoise the image, obtaining significantly higher quality, comparing with BM3D. Next, we demonstrate that latent vectors recovered from noisy images exhibit a consistent bias. By subtracting this bias before projecting back to image space, we improve denoising results even further. Finally, even for unseen images, our method performs better at denoising better than BM3D. Notably, the basic version of our method (without bias correction) requires no prior knowledge on the noise variance. To achieve the highest possible denoising quality, the best performing signal processing based methods, such as BM3D, require an estimate of the blur kernel.

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。

↑