arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.02582cs.CVeess.IV
收藏

深度稀疏光场重聚焦

Deep Sparse Light Field Refocusing

Tel-Aviv University(特拉维夫大学)

Shachar Ben Dayan, David Mendlovic, Raja Giryes

摘要:

光场摄影能够记录4D图像,包含场景的角度信息以及空间信息。光场成像的重要应用之一是捕获后重聚焦。当前的方法为此目的需要密集的角度视野;这些可以用微透镜系统或压缩系统来获取。这两种技术都有需要考虑的主要缺点,包括庞大的结构和角空间分辨率的权衡。我们提出了一种新的实现数字重聚焦的稀疏角度信息的基础上,使用神经网络。这允许记录有利于角分辨率的高空间分辨率,从而使得能够设计具有改进的硬件以及压缩系统的更好性能的紧凑且简单的设备。我们使用一种新的卷积神经网络,其相对较小的结构,使快速重建低内存消耗。此外,它允许在不重新训练各种重聚焦范围和噪声水平的情况下进行处理。结果表明,与现有的方法相比,有很大的改进。

英文摘要:

Light field photography enables to record 4D images, containing angular information alongside spatial information of the scene. One of the important applications of light field imaging is post-capture refocusing. Current methods require for this purpose a dense field of angle views; those can be acquired with a micro-lens system or with a compressive system. Both techniques have major drawbacks to consider, including bulky structures and angular-spatial resolution trade-off. We present a novel implementation of digital refocusing based on sparse angular information using neural networks. This allows recording high spatial resolution in favor of the angular resolution, thus, enabling to design compact and simple devices with improved hardware as well as better performance of compressive systems. We use a novel convolutional neural network whose relatively small structure enables fast reconstruction with low memory consumption. Moreover, it allows handling without re-training various refocusing ranges and noise levels. Results show major improvement compared to existing methods.

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。

↑