arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.09061cs.CV
收藏

基于2D-3D-2D循环的语义对应

Semantic Correspondence via 2D-3D-2D Cycle

Shanghai Jiao Tong University(上海交通大学)

Yang You, Chengkun Li, Yujing Lou, Zhoujun Cheng, Lizhuang Ma, Cewu Lu, Weiming Wang

摘要:

视觉语义对应是计算机视觉中的一个重要课题,可以帮助机器理解我们日常生活中的物体。然而,大多数以前的方法直接训练在2D图像中的对应,这是端到端的,但丢失了大量的信息在3D空间。在本文中,我们提出了一种新的方法来预测语义对应关系,利用它到3D域,然后投影相应的3D模型回到2D域,其语义标签。我们的方法利用了3D视觉的优势,可以明确地推理对象的自遮挡和可见性。我们表明,我们的方法提供了比较,甚至优于标准的语义基准的结果。我们还进行了全面和详细的实验来分析我们的网络组件。代码和实验可在www.example.com上公开获得。

英文摘要:

Visual semantic correspondence is an important topic in computer vision and could help machine understand objects in our daily life. However, most previous methods directly train on correspondences in 2D images, which is end-to-end but loses plenty of information in 3D spaces. In this paper, we propose a new method on predicting semantic correspondences by leveraging it to 3D domain and then project corresponding 3D models back to 2D domain, with their semantic labels. Our method leverages the advantages in 3D vision and can explicitly reason about objects self-occlusion and visibility. We show that our method gives comparative and even superior results on standard semantic benchmarks. We also conduct thorough and detailed experiments to analyze our network components. The code and experiments are publicly available at https://github.com/qq456cvb/SemanticTransfer.

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。

↑