论文标题
SSCNAV：视觉语义导航的置信度 - 感知语义场景完成
SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation
论文作者
论文摘要
本文着重于视觉语义导航，这是为活动代理在未知环境中导航到指定目标对象类别的动作的任务。为了完成此任务，该算法应同时找到并导航到该类别的实例。与传统的点目标导航相比，此任务要求代理在室内环境之前具有更强的上下文。我们介绍了SSCNAV，这是一种算法，该算法使用信心感知的语义场景完成模块明确对场景进行建模，以完成场景并指导代理商的导航计划。鉴于对环境的部分观察，SSCNAV首先用语义标签呈现出未观察到的场景的完整场景表示形式，以及与其自身预测相关的置信图。然后，政策网络从场景完成结果和置信度图中渗透了动作。我们的实验表明，提出的场景完成模块提高了下游导航政策的效率。视频，代码和数据：https：//sscnav.cs.columbia.edu/
This paper focuses on visual semantic navigation, the task of producing actions for an active agent to navigate to a specified target object category in an unknown environment. To complete this task, the algorithm should simultaneously locate and navigate to an instance of the category. In comparison to the traditional point goal navigation, this task requires the agent to have a stronger contextual prior to indoor environments. We introduce SSCNav, an algorithm that explicitly models scene priors using a confidence-aware semantic scene completion module to complete the scene and guide the agent's navigation planning. Given a partial observation of the environment, SSCNav first infers a complete scene representation with semantic labels for the unobserved scene together with a confidence map associated with its own prediction. Then, a policy network infers the action from the scene completion result and confidence map. Our experiments demonstrate that the proposed scene completion module improves the efficiency of the downstream navigation policies. Video, code, and data: https://sscnav.cs.columbia.edu/
