论文标题
基于深度的语义场景完成，具有重要性意识损失
Depth Based Semantic Scene Completion with Position Importance Aware Loss
论文作者
论文摘要
语义场景完成（SSC）是指推断场景的3D语义分割的任务，同时完成3D形状。我们提出了基于单个深度的SSC的新型混合网络Palnet。 Palnet利用一个两流网络使用细粒度深度信息从多阶段提取2D和3D特征，以有效地捕获上下文以及场景的几何提示。 SSC的当前方法对场景的所有部分都同样对物体内部的不必要注意。为了解决这个问题，我们提出了职位意识损失（PA-loss），这在训练网络时意识到位置重要性。具体而言，PA-Loss认为局部几何各向异性可以确定场景中不同位置的重要性。它有益于恢复关键细节，例如物体的边界和场景的角落。在两个基准数据集上进行的全面实验证明了该方法的有效性及其出色的性能。可以在以下网址找到模型和视频演示。
Semantic Scene Completion (SSC) refers to the task of inferring the 3D semantic segmentation of a scene while simultaneously completing the 3D shapes. We propose PALNet, a novel hybrid network for SSC based on single depth. PALNet utilizes a two-stream network to extract both 2D and 3D features from multi-stages using fine-grained depth information to efficiently captures the context, as well as the geometric cues of the scene. Current methods for SSC treat all parts of the scene equally causing unnecessary attention to the interior of objects. To address this problem, we propose Position Aware Loss(PA-Loss) which is position importance aware while training the network. Specifically, PA-Loss considers Local Geometric Anisotropy to determine the importance of different positions within the scene. It is beneficial for recovering key details like the boundaries of objects and the corners of the scene. Comprehensive experiments on two benchmark datasets demonstrate the effectiveness of the proposed method and its superior performance. Models and Video demo can be found at: https://github.com/UniLauX/PALNet.
