Abstract | ||
---|---|---|
This paper presents a 3D modeling system designed for Multi-view Video plus Depth (MVD) sequences. The aim is to remove redundancy in both texture and depth information present in the MVD data. To this end, a volumetric framework is employed in order to merge the input depth maps. Hereby a variant of the Space Carving algorithm is proposed. Voxels are iteratively carved by ray-casting from each view, until the 3D model be geometrically consistent with every input depth map. A surface mesh is then extracted from this volumetric representation thanks to the Marching Cubes algorithm. Subsequently, to address the issue of texture modeling, a new algorithm for multi-texturing the resulting surface is presented. This algorithm selects from the set of input images the best texture candidate to map a given mesh triangle. The best texture is chosen according to a photoconsistency metric. Tests and results are provided using still images from usual MVD test-sequences. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1117/12.908608 | Proceedings of SPIE |
Keywords | Field | DocType |
Multi-view Video plus Depth (MVD),3DTV,FTV,depth map fusion,Space Carving,multi-view texture mapping | Voxel,Computer vision,Space carving,Computer graphics (images),Marching cubes,Texture modeling,Redundancy (engineering),Artificial intelligence,Depth map,Merge (version control),3D modeling,Physics | Conference |
Volume | ISSN | Citations |
8290 | 0277-786X | 0 |
PageRank | References | Authors |
0.34 | 4 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
youssef alj | 1 | 0 | 0.34 |
guillaume boisson | 2 | 1 | 0.69 |
philippe bordes | 3 | 0 | 0.68 |
Muriel Pressigout | 4 | 291 | 15.52 |
L. Morin | 5 | 137 | 35.63 |