Dense Image Registration and Deformable Surface Reconstruction in Presence of Occlusions and Minimal Texture

@article{Ngo2015DenseIR,
  title={Dense Image Registration and Deformable Surface Reconstruction in Presence of Occlusions and Minimal Texture},
  author={Dat Tien Ngo and Sanghyuk Park and Anne Jorstad and Alberto Crivellaro and Chang Dong Yoo and Pascal Fua},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={2273-2281}
}
Deformable surface tracking from monocular images is well-known to be under-constrained. Occlusions often make the task even more challenging, and can result in failure if the surface is not sufficiently textured. In this work, we explicitly address the problem of 3D reconstruction of poorly textured, occluded surfaces, proposing a framework based on a template-matching approach that scales dense robust features by a relevancy score. Our approach is extensively compared to current methods… CONTINUE READING

From This Paper

Topics from this paper.
6 Citations
41 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 41 references

Similar Papers

Loading similar papers…