Abstract | ||
---|---|---|
This paper presents an artifact-free super resolution texture mapping from multiple-view images. The multiple-view images are upscaled with a learning-based super resolution technique and are mapped onto a 3D mesh model. However, mapping multiple-view images onto a 3D model is not an easy task, because artifacts may appear when different upscaled images are mapped onto neighboring meshes. We define a cost function that becomes large when artifacts appear on neighboring meshes, and our method seeks the image-and mesh assignment that minimizes the cost function. Experimental results with real images demonstrate the effectiveness of our method. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICPR.2010.449 | ICPR |
Keywords | Field | DocType |
image resolution,image texture,learning (artificial intelligence),mesh generation,realistic images,solid modelling,3D mesh model,artifact-free super resolution texture mapping,cost function,image-and mesh assignment,learning-based super resolution technique,multiple view images,neighboring meshes,real images,super-resolution texture mapping,upscaled images,graph cut,super resolution,texture mapping | Cut,Computer vision,Texture mapping,Polygon mesh,Pattern recognition,Image texture,Computer science,Artificial intelligence,Solid modeling,Real image,Image resolution,Mesh generation | Conference |
Citations | PageRank | References |
1 | 0.34 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Masaaki Iiyama | 1 | 17 | 14.23 |
Koh Kakusho | 2 | 83 | 20.96 |
Michihiko Minoh | 3 | 349 | 58.69 |