- 15/01/2017 -- 24/12/2018
- 0.00 Eur.
- This is a research and development project funded by the Imprensa Nacional Casa da Moeda (INCM)
- Nuno Gonçalves
- Leandro Cruz
- Leandro Dihl
- Dirce Celorico
Presentation of a content-aware filtering for 2.5D meshes of faces. An exemplar-based filter that corrects each point of a given mesh through local model-exemplar neighborhood comparison taking advantage of prior knowledge of the models (faces) to improve the comparison.
Method for filtering the depth model, reconstructed from light field cameras, based on the removal of low confidence reconstructed values and using an inpainting method to replace them. This approach has shown good results for outliers removal.
A content-aware filtering for 2.5D meshes of faces that preserves their intrinsic features. We take advantage of prior knowledge of the models (faces) to improve the comparison. The model is invariant to depth translation and scale. The proposed method is evaluated on a public 3D face dataset with different levels of noise. The results show that the method is able to remove noise without smoothing the sharp features of the face.
Presented a filtering method for meshes of faces preserving their intrinsic features. It is based in an exemplar-based neighborhood matching where all models are in a frontal position avoiding rotation and perspective drawbacks. Moreover, the model is invariant to depth translation and scale.