Recursive Live Dense Reconstruction: Some comments on established and imaginable new approaches

In the present position paper, I formulate some (in part critical) remarks related to some techniques which are successfully used in contemporary live dense reconstruction approaches. Main issues are feature based correspondence vs. image-based matching, the generalization of the brightness constancy assumption, and the handling of featureless regions which do not allow direct determination of correspondence.

[1]  Andrew J. Davison,et al.  DTAM: Dense tracking and mapping in real-time , 2011, 2011 International Conference on Computer Vision.

[2]  Daniel Cremers,et al.  Stereoscopic Scene Flow Computation for 3D Motion Understanding , 2011, International Journal of Computer Vision.

[3]  Rudolf Mester,et al.  Illumination-Robust Dense Optical Flow Using Census Signatures , 2011, DAGM-Symposium.

[4]  Marin Ferecatu,et al.  Interactive Search for Image Categories by Mental Matching , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[5]  Uwe Franke,et al.  6D-Vision: Fusion of Stereo and Motion for Robust Environment Perception , 2005, DAGM-Symposium.

[6]  Andrew W. Fitzgibbon,et al.  Global stereo reconstruction under second order smoothness priors , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  R. Mester,et al.  Robust displacement vector estimation including a statistical error analysis , 1995 .

[8]  Daniel Cremers,et al.  An Unbiased Second-Order Prior for High-Accuracy Motion Estimation , 2008, DAGM-Symposium.