Title | ||
---|---|---|
Viewpoint invariant 3D landmark model inference from monocular 2D images using higher-order priors |
Abstract | ||
---|---|---|
In this paper, we propose a novel one-shot optimization approach to simultaneously determine both the optimal 3D landmark model and the corresponding 2D projections without explicit estimation of the camera viewpoint, which is also able to deal with misdetections as well as partial occlusions. To this end, a 3D shape manifold is built upon fourth-order interactions of landmarks from a training set where pose-invariant statistics are obtained in this space. The 3D-2D consistency is also encoded in such high-order interactions, which eliminate the necessity of viewpoint estimation. Furthermore, the modeling of visibility improves further the performance of the method by handling missing correspondences and occlusions. The inference is addressed through a MAP formulation which is naturally transformed into a higher-order MRF optimization problem and is solved using a dual-decomposition-based method. Promising results on standard face benchmarks demonstrate the potential of our approach. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICCV.2011.6126258 | ICCV |
Keywords | Field | DocType |
optimisation,map formulation,higher-order interactions,pose-invariant statistics,dual-decomposition-based method,camera viewpoint,image processing,higher-order mrf optimization problem,viewpoint invariant,statistical analysis,fourth-order interactions,viewpoint invariant 3d landmark model inference,one-shot optimization approach,higher-order prior,monocular 2d images,3d shape manifold,landmark model,high-order interaction,novel one-shot optimization approach,2d projections,landmark model inference,3d-2d consistency,explicit estimation,viewpoint estimation,fourth-order interaction,estimation,solid modeling,higher order,computational modeling,three dimensional,natural transformation,shape,optimization problem,computer model | Computer vision,Pattern recognition,Inference,Computer science,Image processing,Artificial intelligence,Solid modeling,Invariant (mathematics),Prior probability,Landmark,Monocular,Optimization problem | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1550-5499 |
ISBN | Citations | PageRank |
978-1-4577-1101-5 | 7 | 0.44 |
References | Authors | |
17 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chaohui Wang | 1 | 193 | 9.30 |
Yun Zeng | 2 | 82 | 4.30 |
Loic Simon | 3 | 83 | 4.94 |
Ioannis A. Kakadiaris | 4 | 1910 | 203.66 |
Dimitris Samaras | 5 | 1740 | 101.49 |
Nikos Paragios | 6 | 6055 | 387.68 |