3D point cloud segmentation remains challenging for structureless and textureless regions. We present a new unified point-based framework for 3D point cloud segmentation that effectively optimizes pixel-level features, geometrical structures and global context priors of an entire scene. By back-projecting 2D image features into 3D coordinates, our network learns 2D textural appearance and 3D structural features in a unified framework. In addition, we investigate a global context prior to obtain a better prediction. We evaluate our framework on ScanNet online benchmark and show that our method outperforms several state-of-the-art approaches. We explore synthesizing camera poses in 3D reconstructed scenes for achieving higher performance. In-depth analysis on feature combinations and synthetic camera pose verifies that features from different modalities benefit each other and dense camera pose sampling further improves the segmentation results.

针对3D点云的分割问题，我们提出了一种新的点云分割框架，该框架能有效地优化整个场景的像素级特征，几何结构和全局上下文先验。实验结果表明，该方法优于现有的一些最先进的方法，并探讨了在三维重建场景中合成相机姿态以获得更高的性能。

一个统一的基于点的3D分割框架