arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.02993cs.CVcs.LGeess.IV
收藏

考虑场景对称性的单一法向视场球面像生成

Spherical Image Generation from a Single Normal Field of View Image by Considering Scene Symmetry

The University of Tokyo(东京大学);Riken(理化学研究所)

Takayuki Hara, Tatsuya Harada

摘要:

在所有方向(360度)拍摄的球形图像可以代表主体的周围环境和空间本身,为观众提供身临其境的体验。从单个法向视场(NFOV)图像生成球形图像是方便的,并且大大扩展了使用场景,因为不需要使用特定的全景相机或从多个方向拍摄图像;然而,这仍然是一个具有挑战性且未解决的问题。主要的挑战是控制在生成包括期望的似真球面图像的所有方向的宽区域中所涉及的高自由度。另一方面,场景对称性是球面图像全局结构的一个基本性质,如旋转对称性、平面对称性和非对称性。我们提出了一种方法来生成球形图像从一个单一的NFOV图像,并控制自由度的生成区域使用场景对称性。我们将场景对称性参数作为潜变量纳入条件变分自编码器中,然后我们学习NFOV图像和场景对称性的球形图像的条件概率。此外,概率密度函数表示使用神经网络,和场景对称性实现使用循环移位和翻转的隐变量。实验结果表明,该方法可以生成从对称到非对称的各种逼真的球面图像。

英文摘要:

Spherical images taken in all directions (360 degrees) allow representing the surroundings of the subject and the space itself, providing an immersive experience to the viewers. Generating a spherical image from a single normal-field-of-view (NFOV) image is convenient and considerably expands the usage scenarios because there is no need to use a specific panoramic camera or take images from multiple directions; however, it is still a challenging and unsolved problem. The primary challenge is controlling the high degree of freedom involved in generating a wide area that includes the all directions of the desired plausible spherical image. On the other hand, scene symmetry is a basic property of the global structure of the spherical images, such as rotation symmetry, plane symmetry and asymmetry. We propose a method to generate spherical image from a single NFOV image, and control the degree of freedom of the generated regions using scene symmetry. We incorporate scene-symmetry parameters as latent variables into conditional variational autoencoders, following which we learn the conditional probability of spherical images for NFOV images and scene symmetry. Furthermore, the probability density functions are represented using neural networks, and scene symmetry is implemented using both circular shift and flip of the hidden variables. Our experiments show that the proposed method can generate various plausible spherical images, controlled from symmetric to asymmetric.

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。

↑