In this paper we learn a statistical wavelet prior of the shape of the human face and use it to constrain stereo reconstruction within a Bayesian framework. We ...

Abstract—When reconstructing a specific type or class of object using stereo, we can leverage prior knowledge of the shape of that type of object.

In this paper we learn a statistical wavelet prior of the shape of the human face and use it to constrain stereo reconstruction within a Bayesian framework. We ...

Our method is fast, and is robust to noise and outliers. Additionally, we obtain a shape in an parameterized and corresponded shape space, making it ready for ...

Apr 25, 2024 · Wavelet Model-based Stereo for Fast, Robust Face Reconstruction. CRV ... Image-based Model Completion. 3DIM 2007: 305-311; 2006. [c2].

Wavelet Model-based Stereo for Fast, Robust Face Reconstruction. A. Brunton, J. Lang, E. Dubois, Chang Shu. 2011, Canadian Conference on Computer and Robot ...

Wavelet model-based stereo for fast, robust face reconstruction‏. A Brunton, J Lang, E Dubois, C Shu‏. 2011 Canadian Conference on Computer and Robot Vision, ...

We present a statistical model for 3D human faces in varying expression, which decomposes the surface of the face using a wavelet transform.

Wavelet model-based stereo for fast, robust face reconstruction. In: Canadian Conference on Computer and Robot Vision (CRV), pp. 347-354. Crossref · Google ...