arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.02252eess.IVcs.CV
收藏

用于光场重建的空间-角度注意力网络

Spatial-Angular Attention Network for Light Field Reconstruction

Northeastern University(东北大学);Tsinghua University(清华大学)

Gaochang Wu, Yingqian Wang, Yebin Liu, Lu Fang, Tianyou Chai

摘要:

典型的基于学习的光场重建方法需要通过加深网络来构建大的感受野,以捕获输入视图之间的对应关系。在本文中,我们提出了一个空间-角度的注意力网络,感知光场中的非本地的对应关系,并在端到端的方式重建高角度分辨率的光场。受非局部注意机制的启发,专门针对高维光场数据的空间-角度注意模块被引入,以计算光场中每个像素在极平面中的所有位置的响应,并生成沿着角度维度捕获对应关系的注意图。然后,我们提出了一个多尺度重建结构,有效地实现在低空间尺度的非局部注意,同时也保留在高空间尺度的高频分量。大量的实验表明,所提出的空间-角度注意力网络的优越性能,用于重建稀疏采样的光场与非朗伯效应。

英文摘要:

Typical learning-based light field reconstruction methods demand in constructing a large receptive field by deepening the network to capture correspondences between input views. In this paper, we propose a spatial-angular attention network to perceive correspondences in the light field non-locally, and reconstruction high angular resolution light field in an end-to-end manner. Motivated by the non-local attention mechanism, a spatial-angular attention module specifically for the high-dimensional light field data is introduced to compute the responses from all the positions in the epipolar plane for each pixel in the light field, and generate an attention map that captures correspondences along the angular dimension. We then propose a multi-scale reconstruction structure to efficiently implement the non-local attention in the low spatial scale, while also preserving the high frequency components in the high spatial scales. Extensive experiments demonstrate the superior performance of the proposed spatial-angular attention network for reconstructing sparsely-sampled light fields with non-Lambertian effects.

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。

↑