Removing fences from sweep motion videos using global 3D reconstruction and fence-aware light field rendering
Removing fences from sweep motion videos using global 3D reconstruction and fence-aware light field rendering
复制标题
使用全局 3D 重建和栅栏感知光场渲染从扫描运动视频中移除栅栏
DOI：
10.1007/s41095-018-0126-8
复制
发表时间：
2018
影响因子：
6.9
通讯作者：
and Saito Hideo
中科院分区：
文献类型：
--
作者：
Lueangwattana Chanya;Mori Shohei;and Saito Hideo
由于栅栏的特性（薄、缺乏纹理等），减少图像中栅栏的外观是一个具有挑战性的研究领域。以及对被遮挡背景恢复的需要。在本文中，我们描述了一个栅栏去除方法，由用户进行扫描运动，其中被遮挡的背景是潜在的观察到的图像序列。为了利用几何和外观信息，如连续图像，我们使用两个众所周知的方法：结构从运动和光场渲染。使用真实的图像序列的结果表明，我们的方法可以稳定地分割围栏和保护各种围栏和背景组合的背景细节。可以成功地提供具有帧相干性的没有栅栏的新视频。
Diminishing the appearance of a fence in an image is a challenging research area due to the characteristics of fences (thinness, lack of texture, etc.) and the need for occluded background restoration. In this paper, we describe a fence removal method for an image sequence captured by a user making a sweep motion, in which occluded background is potentially observed. To make use of geometric and appearance information such as consecutive images, we use two well-known approaches: structure from motion and light field rendering. Results using real image sequences show that our method can stably segment fences and preserve background details for various fence and background combinations. A new video without the fence, with frame coherence, can be successfully provided.