资源论文Blocks World Revisited: Image Understanding Using Qualitative Geometry and Mechanics

Blocks World Revisited: Image Understanding Using Qualitative Geometry and Mechanics

2020-03-31 | |  71 |   36 |   0

Abstract

Since most current scene understanding approaches operate either on the 2D image or using a surface-based representation, they do not allow reasoning about the physical constraints within the 3D scene. Inspired by the “Blocks World” work in the 1960’s, we present a qual- itative physical representation of an outdoor scene where ob jects have volume and mass, and relationships describe 3D structure and mechani- cal configurations. Our representation allows us to apply powerful global geometric constraints between 3D volumes as well as the laws of statics in a qualitative manner. We also present a novel iterative “interpretation- by-synthesis” approach where, starting from an empty ground plane, we progressively “build up” a physically-plausible 3D interpretation of the image. For surface layout estimation, our method demonstrates an im- provement in performance over the state-of-the-art [9]. But more impor- tantly, our approach automatically generates 3D parse graphs which describe qualitative geometric and mechanical properties of ob jects and relationships between ob jects within an image.

上一篇:Monocular 3D Scene Modeling and Inference: Understanding Multi-Object Traffic Scenes

下一篇:Bilinear Factorization via Augmented Lagrange Multipliers*

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...