Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects
Authors:
- Muhammad Zeeshan ZiaMZMuhammad Zeeshan Zia
- Michael StarkMSMichael Stark
- Konrad SchindlerKSKonrad Schindler
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3678-3685
Abstract
Current systems for scene understanding typically represent objects as 2D or 3D bounding boxes. While these representations have proven robust in a variety of applications, they provide only coarse approximations to the true 2D and 3D extent of objects. As a result, object-object interactions, such as occlusions or ground-plane contact, can be represented only superficially. In this paper, we approach the problem of scene understanding from the perspective of 3D shape modeling, and design a 3D scene representation that reasons jointly about the 3D shape of multiple objects. This representation allows to express 3D geometry and occlusion on the fine detail level of individual vertices of 3D wireframe models, and makes it possible to treat dependencies between objects, such as occlusion reasoning, in a deterministic way. In our experiments, we demonstrate the benefit of jointly estimating the 3D shape of multiple objects in a scene over working with coarse boxes, on the recently proposed KITTI dataset of realistic street scenes.Keywords
This publication has 27 references indexed in Scilit:
- Understanding Bayesian Rooms Using Composite 3D Object Models2013
- Explicit Occlusion Modeling for 3D Object Class Representations2013
- Detailed 3D Representations for Object Recognition and ModelingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Fine-Grained Categorization for 3D Scene Understanding2012
- 3D2PM – 3D Deformable Part Models2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Putting Objects in PerspectiveInternational Journal of Computer Vision, 2008
- Three-dimensional object recognition from single two-dimensional imagesArtificial Intelligence, 1987
- Symbolic reasoning among 3-D models and 2-D imagesArtificial Intelligence, 1981
- Representation and recognition of the spatial organization of three-dimensional shapesProceedings of the Royal Society of London. B. Biological Sciences, 1978