arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.04568cs.CVcs.HC
收藏

180-从单个图像进行度外绘

180-degree Outpainting from a Single Image

The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Zhenqiang Ying, Alan Bovik

摘要:

向观看者的周边视觉呈现上下文图像是增强沉浸式视觉体验的最有效的技术之一。然而,大多数图像仅呈现窄视图,因为标准相机的视场(FoV)很小。为了克服这一限制,我们提出了一种深度学习方法,该方法学习从窄视角图像预测180°全景图像。具体来说,我们设计了一个中心凹框架,适用于近周边和中周边地区的不同策略。两个网络分别训练,然后联合使用,依次执行窄至90°生成和90°至180°生成。然后将生成的输出与其对齐的输入融合,以生成扩展的等矩形图像供查看。我们的实验结果表明,使用深度学习的单视图到全景图像生成是可行的和有前途的。

英文摘要:

Presenting context images to a viewer's peripheral vision is one of the most effective techniques to enhance immersive visual experiences. However, most images only present a narrow view, since the field-of-view (FoV) of standard cameras is small. To overcome this limitation, we propose a deep learning approach that learns to predict a 180° panoramic image from a narrow-view image. Specifically, we design a foveated framework that applies different strategies on near-periphery and mid-periphery regions. Two networks are trained separately, and then are employed jointly to sequentially perform narrow-to-90° generation and 90°-to-180° generation. The generated outputs are then fused with their aligned inputs to produce expanded equirectangular images for viewing. Our experimental results show that single-view-to-panoramic image generation using deep learning is both feasible and promising.

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。

↑