论文标题
FOV-net：使用自我注意力和不确定性的视野外推
FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty
论文作者
论文摘要
对周围环境做出有根据的预测的能力，并以一定的信心将它们联系起来，对于智能系统，例如自动驾驶汽车和机器人都很重要。它允许他们提早计划并做出相应的决定。在这一观察中，在本文中，我们利用来自带有狭窄视野的视频序列的信息来推断更广泛的视野。为此，我们提出了一个时间上一致的视野外推框架，即fov-net，即：（1）利用3D信息来传播过去框架的观察到的场景部分； （2）使用基于注意力的特征聚合模块和一个封闭式的自我发项模块汇总了传播的多帧信息，同时幻觉了任何未观察到的场景部分； （3）在每个像素上分配一个可解释的不确定性值。广泛的实验表明，FOV-NET不仅比现有替代方案更好地推断了时间一致的视野场景，而且还提供了相关的不确定性，这些不确定性可能使下游应用程序的关键决策受益。项目页面位于http://charliemememory.github.io/ral21_fov。
The ability to make educated predictions about their surroundings, and associate them with certain confidence, is important for intelligent systems, like autonomous vehicles and robots. It allows them to plan early and decide accordingly. Motivated by this observation, in this paper we utilize information from a video sequence with a narrow field-of-view to infer the scene at a wider field-of-view. To this end, we propose a temporally consistent field-of-view extrapolation framework, namely FoV-Net, that: (1) leverages 3D information to propagate the observed scene parts from past frames; (2) aggregates the propagated multi-frame information using an attention-based feature aggregation module and a gated self-attention module, simultaneously hallucinating any unobserved scene parts; and (3) assigns an interpretable uncertainty value at each pixel. Extensive experiments show that FoV-Net does not only extrapolate the temporally consistent wide field-of-view scene better than existing alternatives, but also provides the associated uncertainty which may benefit critical decision-making downstream applications. Project page is at http://charliememory.github.io/RAL21_FoV.
