arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1704.03568cs.CVq-bio.NCstat.ML
收藏

超越平面对称性:模拟人类在野外对反射和旋转对称性的感知

Beyond Planar Symmetry: Modeling human perception of reflection and rotation symmetries in the wild

The Pennsylvania State University(宾夕法尼亚州立大学)

Christopher Funk, Yanxi Liu

摘要:

人类利用现实世界的对称性来完成各种任务,但用计算模型来捕捉他们高超的对称感知机制仍然是难以捉摸的。受一项新研究的启发,该研究展示了人类在野外感知对称性的极高的人际准确性,我们构建了第一个用于反射和旋转对称性检测的深度学习神经网络(Sym-NET),该网络在MS-COCO(Microsoft-Common Object in COontext)数据集的照片上进行训练,该数据集具有来自400多名人类观察者的近11 K个一致性标签。我们采用新颖的方法将离散的人类标签转换为对称热图,在图像中密集地捕获对称性,并针对多种现有的计算机视觉算法定量评估Sym-NET。在CVPR 2013对称竞争测试集和未见过的MS-COCO照片上,Sym-NET明显优于所有其他竞争对手。除了在平面上数学上定义良好的对称性之外,Sym-NET还展示了识别视点变化的3D对称性,部分遮挡的对称对象以及语义级别的对称性的能力。

英文摘要:

Humans take advantage of real world symmetries for various tasks, yet capturing their superb symmetry perception mechanism with a computational model remains elusive. Motivated by a new study demonstrating the extremely high inter-person accuracy of human perceived symmetries in the wild, we have constructed the first deep-learning neural network for reflection and rotation symmetry detection (Sym-NET), trained on photos from MS-COCO (Microsoft-Common Object in COntext) dataset with nearly 11K consistent symmetry-labels from more than 400 human observers. We employ novel methods to convert discrete human labels into symmetry heatmaps, capture symmetry densely in an image and quantitatively evaluate Sym-NET against multiple existing computer vision algorithms. On CVPR 2013 symmetry competition testsets and unseen MS-COCO photos, Sym-NET significantly outperforms all other competitors. Beyond mathematically well-defined symmetries on a plane, Sym-NET demonstrates abilities to identify viewpoint-varied 3D symmetries, partially occluded symmetrical objects, and symmetries at a semantic level.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑