Corpus ID: 203598656

POINT-BASED SIMILARITY ESTIMATION BETWEEN 2 . 5 D VISUAL HULLS AND 3 D OBJECTS

@inproceedings{Moustakas2012POINTBASEDSE,
  title={POINT-BASED SIMILARITY ESTIMATION BETWEEN 2 . 5 D VISUAL HULLS AND 3 D OBJECTS},
  author={Konstantinos Moustakas and Georgios Stavropoulos and Dimitrios Tzovaras},
  year={2012}
}
This paper presents a novel framework for point-based similarity estimation between 3D objects and 2.5D visual hulls. Initially, the protrusion map is estimated for both the visual hull that is generated by a range image and the 3D model that is followed by the extraction of the salient features that correspond to the highly protruding areas of the objects. Then, based on the concept that for a 3D object and a corresponding query range image, there should be a virtual camera with such intrinsic… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 27 REFERENCES
3-D Model Search and Retrieval From Range Images Using Salient Features
TLDR
This paper presents a novel framework for partial matching and retrieval of 3-D models based on a query-by-range-image approach, and a novel method is also proposed to hierarchically search in the parameter space for the optimum solution. Expand
3D object recognition using shape similiarity-based aspect graph
  • C. Cyr, B. Kimia
  • Mathematics
  • Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001
  • 2001
We present an aspect-graph approach to 3D object recognition where the definition of an aspect is motivated by its role in the subsequent recognition step. Specifically, we measure the similarityExpand
Topology matching for fully automatic similarity estimation of 3D shapes
TLDR
A novel technique is proposed, called Topology Matching, in which similarity between polyhedral models is quickly, accurately, and automatically calculated by comparing Multiresolutional Reeb Graphs (MRGs), which operates well as a search key for 3D shape data sets. Expand
On Visual Similarity Based 3D Model Retrieval
TLDR
A visual similarity‐based 3D model retrieval system that is robust against similarity transformation, noise, model degeneracy, and provides 42%, 94% and 25% better performance than three other competing approaches. Expand
Geometric Matching for Free-Form 3D Object Recognition
TLDR
A new approach to the recognition of 3D objects of arbitrary shape using geometric 3D models and geometric matching which provides a perspective to escape the difficulties found with the classical segmentation and primitive extraction approach. Expand
Registering Multiview Range Data to Create 3D Computer Objects
TLDR
The effectiveness with which registration of range images can be accomplished makes this method attractive for many practical applications where surface models of 3D objects must be constructed. Expand
Spectral-Driven Isometry-Invariant Matching of 3D Shapes
TLDR
A matching method for 3D shapes, which comprises a new technique for surface sampling and two algorithms for matching3D shapes based on point-based statistical shape descriptors, which is faster than using the bipartite graph matching and it has a similar retrieval effectiveness. Expand
View-based 3-D object recognition using shock graphs
TLDR
This work extends previous work in both shock graph matching and hierarchical structure indexing to propose the first unified framework for view-based 3-D object recognition using shock graphs, with an improved spectral characterization of shock graph structure that drives a powerful indexing mechanism and drives a matching algorithm that can accommodate noise and occlusion. Expand
Automatic Pose Estimation for Range Images on the GPU
TLDR
This work proposes a fast method for automatic pose estimation without manual initialization based on shape matching of a 3D model to a range image of the scene and developed a new error function to compare the input range image to pre-computed range maps of the3D model. Expand
Scale-space representation of 3D models and topological matching
TLDR
A framework for shape matching through scale-space decomposition of 3D models through spectral decomposition is presented, based on recent developments in efficient hierarchical decomposing of metric data using its spectral properties. Expand
...
1
2
3
...