论文标题
MMGSD：多模式高斯形状描述符，以匹配1D和2D可变形对象
MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects
论文作者
论文摘要
我们探索了在不同配置中可变形对象的图像之间的学习pixelwise对应关系。传统的对应匹配方法（例如SIFT，SURF和ORB）可能无法提供足够的上下文信息来进行细粒度的操作。我们提出了多模式高斯形状描述符（MMGSD），这是一种可变形对象的新的视觉表示，将思想从密集的对象描述符扩展到了，以预测不同对象配置之间的所有对称对应。 MMGSD以一种自制的方式从合成数据中学习，并产生与可测量不确定性的对应热图。在仿真中，实验表明MMGSD可以分别获得32.4和31.3的RMSE，分别用于平方布和编织的合成尼龙绳。结果表明，基于对比度学习，对称像素对比度损失（SPCL）的基线平均提高了47.7％，而不是强制执行分布连续性的MMGSD。
We explore learning pixelwise correspondences between images of deformable objects in different configurations. Traditional correspondence matching approaches such as SIFT, SURF, and ORB can fail to provide sufficient contextual information for fine-grained manipulation. We propose Multi-Modal Gaussian Shape Descriptor (MMGSD), a new visual representation of deformable objects which extends ideas from dense object descriptors to predict all symmetric correspondences between different object configurations. MMGSD is learned in a self-supervised manner from synthetic data and produces correspondence heatmaps with measurable uncertainty. In simulation, experiments suggest that MMGSD can achieve an RMSE of 32.4 and 31.3 for square cloth and braided synthetic nylon rope respectively. The results demonstrate an average of 47.7% improvement over a provided baseline based on contrastive learning, symmetric pixel-wise contrastive loss (SPCL), as opposed to MMGSD which enforces distributional continuity.
