Marching cubes: A high resolution 3D surface construction algorithm
SIGGRAPH '87 Proceedings of the 14th annual conference on Computer graphics and interactive techniques
An Algorithm for Finding Best Matches in Logarithmic Expected Time
ACM Transactions on Mathematical Software (TOMS)
The Ball-Pivoting Algorithm for Surface Reconstruction
IEEE Transactions on Visualization and Computer Graphics
The Visual Hull Concept for Silhouette-Based Image Understanding
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fusion of Multi-View Silhouette Cues Using a Space Occupancy Grid
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Poisson surface reconstruction
SGP '06 Proceedings of the fourth Eurographics symposium on Geometry processing
Efficient Polyhedral Modeling from Silhouettes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-view body tracking with a detector-driven hierarchical particle filter
AMDO'12 Proceedings of the 7th international conference on Articulated Motion and Deformable Objects
| Hi-index | 0.00 |
This paper presents a system for 3D reconstruction from video sequences acquired in multi-camera environments. In particular, the 3D surfaces of foreground objects in the scene are extracted and represented by polygon meshes. Three stages are concatenated to process multi-view data. First, a foreground segmentation method extracts silhouettes of objects of interest. Then, a 3D reconstruction strategy obtains a cloud of oriented points that lie on the surfaces of the objects of interest in a spatially bounded volume. Finally, a fast meshing algorithm provides a topologically correct interpolation of the surface points that can be used for both visualization and further mesh processing purposes. The quality of the results (computational load) obtained by our system compares favorably against a baseline system built from state-of-the-art techniques for similar processing times (quality of the results).