张宁 SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
"链接：https://pan.baidu.com/s/1hpwb8IjtEpb3uTIncJbTUg
提取码：0wz1"
Trung T. Pham , Thanh-Toan Do , Niko Sünderhauf , Ian Reid
SceneCut：室内场景的联合几何和对象分割
This paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image. SceneCut’s joint reasoning over scene semantics and geometry allows a robot to detect and segment object instances in complex scenes where modern deep learning-based methods either fail to separate object instances, or fail to detect objects that were not seen during training. SceneCut automatically decomposes a scene into meaningful regions which either represent objects or scene surfaces. The decomposition is qualified by an unified energy function over objectness and geometric fitting. We show how this energy function can be optimized efficiently by utilizing hierarchical segmentation trees. Moreover, we leverage a pretrained convolutional oriented boundary network to predict accurate boundaries from images, which are used to construct high-quality region hierarchies. We evaluate SceneCut on several different indoor environments, and the results show that SceneCut significantly outperforms all the existing methods.
本文介绍了SceneCut，这是一种使用单个RGB-D图像联合发现以前看不见的物体和非物体表面的新方法。SceneCut对场景语义和几何的联合推理允许机器人在复杂场景中检测和分割对象实例，其中现代基于深度学习的方法无法分离对象实例，或者无法检测在训练期间未看到的对象。SceneCut会自动将场景分解为有意义的区域，这些区域代表对象或场景表面。通过对象性和几何拟合的统一能量函数来限定分解。我们展示了如何通过利用分层分割树有效地优化这种能量函数。此外，我们利用预训练的卷积导向边界网络来预测图像的准确边界，这些边界用于构建高质量的区域层次结构。我们在几个不同的室内环境中评估SceneCut，结果表明SceneCut明显优于所有现有方法。