论文标题
3DCFS：快速且稳健的关节3D语义 - 实体通过耦合特征选择
3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection
论文作者
论文摘要
我们通过耦合特征选择（称为3DCFS）提出了一种新颖的快速，稳健的3D点云分割框架，该特征选择共同执行语义和实例分割。受到人类场景感知过程的启发，我们设计了一个新颖的耦合特征选择模块，名为CFSM，该模块可自适应地选择并以耦合方式从两个任务中融合了相互的语义和实例特征。为了进一步提高3DCF中实例分割任务的性能，我们研究了一个损失函数，该损失函数有助于模型学会在训练过程中平衡输出嵌入维度的大小，这使得计算欧几里得距离更可靠并增强了模型的普遍性。广泛的实验表明，在准确性，速度和计算成本方面，我们的3DCF在基准数据集上优于最先进的方法。
We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation. Inspired by the human scene perception process, we design a novel coupled feature selection module, named CFSM, that adaptively selects and fuses the reciprocal semantic and instance features from two tasks in a coupled manner. To further boost the performance of the instance segmentation task in our 3DCFS, we investigate a loss function that helps the model learn to balance the magnitudes of the output embedding dimensions during training, which makes calculating the Euclidean distance more reliable and enhances the generalizability of the model. Extensive experiments demonstrate that our 3DCFS outperforms state-of-the-art methods on benchmark datasets in terms of accuracy, speed and computational cost.
