Name
Abstract | ||
|---|---|---|
In this paper, we present an approach for scene understanding by reasoning physical stability of objects from point cloud. We utilize a simple observation that, by human design, objects in static scenes should be stable with respect to gravity. This assumption is applicable to all scene categories and poses useful constraints for the plausible interpretations (parses) in scene understanding. Our method consists of two major steps: 1) geometric reasoning: recovering solid 3D volumetric primitives from defective point cloud, and 2) physical reasoning: grouping the unstable primitives to physically stable objects by optimizing the stability and the scene prior. We propose to use a novel disconnectivity graph (DG) to represent the energy landscape and use a Swendsen-Wang Cut (MCMC) method for optimization. In experiments, we demonstrate that the algorithm achieves substantially better performance for i) object segmentation, ii) 3D volumetric recovery of the scene, and iii) better parsing result for scene understanding in comparison to state-of-the-art methods in both public dataset and our own new dataset. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/CVPR.2013.402 | CVPR |
Keywords | Field | DocType |
optimisation,image representation,physically stable objects,defective point cloud,human design,unstable primitives,geometric reasoning,scene category,image segmentation,parsing,point cloud,computational geometry,object segmentation,3d volumetric scene recovery,static scenes,beyond point clouds,mcmc method,energy landscape representation,better performance,optimization,disconnectivity graph,scene understanding,static scene,natural scenes,physical reasoning,swendsen-wang cut method,reasoning physical stability,graph theory,public dataset,stability,solid 3d volumetric primitive recovery,scene categories,physical stability reasoning,reasoning geometry,own new dataset,gravity,shape,cognition,stability analysis | Graph theory,Computer vision,Pattern recognition,Markov chain Monte Carlo,Segmentation,Computer science,Computational geometry,Image segmentation,Scene statistics,Artificial intelligence,Parsing,Point cloud | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
45 | 1.24 | 15 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bo Zheng | 1 | 159 | 13.62 |
| Yibiao Zhao | 2 | 322 | 17.17 |
| Joey C. Yu | 3 | 57 | 2.14 |
| Katsushi Ikeuchi | 4 | 4651 | 881.49 |
| Song-Chun Zhu | 5 | 6580 | 741.75 |