Where Does It End? -- Reasoning About Hidden Surfaces by Object Intersection Constraints

CVPR(2020)

引用 2|浏览479
暂无评分
摘要
Dynamic scene understanding is an essential capability in robotics and VR/AR. In this paper we propose Co-Section, an optimization-based approach to 3D dynamic scene reconstruction, which infers hidden shape information from intersection constraints. An object-level dynamic SLAM frontend detects, segments, tracks and maps dynamic objects in the scene. Our optimization backend completes the shapes using hull and intersection constraints between the objects. In experiments, we demonstrate our approach on real and synthetic dynamic scene datasets. We also assess the shape completion performance of our method quantitatively. To the best of our knowledge, our approach is the first method to incorporate such physical plausibility constraints on object intersections for shape completion of dynamic objects in an energy minimization framework.
更多
查看译文
关键词
object intersections,hidden surfaces,object intersection constraints,dynamic scene understanding,essential capability,optimization-based approach,3D dynamic scene reconstruction,shape information,optimization backend,synthetic dynamic scene datasets,shape completion performance,physical plausibility constraints,dynamic object mapping,object-level dynamic SLAM frontend,energy minimization framework
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要