Abstract
We introduce CoSegNet, a deep neural network architecture for co-segmentation of a set of 3D shapes represented as point clouds. CoSegNet takes as input a set of unsegmented shapes, proposes per-shape parts, and then jointly optimizes the part labelings across the set subjected to a novel group consistency loss expressed via matrix rank estimates. The proposals are refined in each iteration by an auxiliary network that acts as a weak regularizing prior, pre-trained to denoise noisy, unlabeled parts from a large collection of segmented 3D shapes, where the part compositions within the same object category can be highly inconsistent. The output is a consistent part labeling for the input set, with each shape segmented into up to K (a user-specified hyperparameter) parts. The overall pipeline is thus weakly supervised, producing consistent segmentations tailored to the test set, without consistent ground-truth segmentations. We show qualitative and quantitative results from CoSegNet and evaluate it via ablation studies and comparisons to state-of-the-art co-segmentation methods.
Abstract (translated)
我们介绍了cosegnet，一种深度神经网络结构，用于对以点云表示的一组三维形状进行共分割。cosegnet将一组未分段的形状作为输入，提出每个形状的部分，然后联合优化整个集合中的部件标签，并通过矩阵秩估计表示一个新的组一致性损失。这些建议在每次迭代中都被一个辅助网络细化，该辅助网络充当弱正则化先验，经过预先训练，可以从大量分割的三维形状集合中消除噪音、未标记的零件，在这些三维形状集合中，同一对象类别中的零件组成可能高度不一致。输出是输入集的一致零件标签，每个形状被分割成最多k（用户指定的超参数）零件。因此，对整个管道进行了弱监控，产生了针对测试集的一致分段，而没有一致的地面真值分段。我们展示了cosegnet的定性和定量结果，并通过消融研究和与最先进的共分割方法的比较对其进行评估。
URL
https://arxiv.org/abs/1903.10297
