Abstract | ||
---|---|---|
When it comes to textured object modelling, the standard practice is to use a multiple views approach. The numerous views allow reconstruction and provide robustness to viewpoint change but yield complex models. This paper shows that robustness with lighter models can be achieved through robust descriptors. A comparison between various descriptors allows choosing the one providing the best viewpoint robustness, in this case the ASIFT descriptor. Then, using this descriptor, the results show, for a wide variety of object shapes, that as few as seventeen views provide a high level of robustness to viewpoint change while being fast to process and having a small memory footprint. This work concludes advocating in favour of modelling methods using robust descriptors and a small number of views. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/978-3-319-23192-1_5 | COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2015, PT I |
Keywords | Field | DocType |
Object modelling, Object recognition, Multiple views, Robust descriptors | Small number,Computer vision,Pattern recognition,Computer science,Object model,Robustness (computer science),Artificial intelligence,Memory footprint,Cognitive neuroscience of visual object recognition | Conference |
Volume | ISSN | Citations |
9256 | 0302-9743 | 1 |
PageRank | References | Authors |
0.35 | 12 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Guido Manfredi | 1 | 4 | 1.15 |
Michel Devy | 2 | 542 | 71.47 |
Daniel Sidobre | 3 | 68 | 8.15 |