Augmenting images of non-rigid scenes using point and curve correspondences
Our goal is to augment images of non-rigid scenes coming from single-camera footage. We do not assume any a priori information about the scene being viewed, such as for example a parameterized 3D model or the motion of the camera. One possible solution is to use non-rigid factorization of points, fr...
Autors principals: | Bartoli, A, von Tunzelmann, E, Zisserman, A |
---|---|
Format: | Conference item |
Idioma: | English |
Publicat: |
IEEE
2004
|
Ítems similars
-
Non-rigid registration of breast images using feature points.
per: Zhang, W, et al.
Publicat: (2010) -
Finding point correspondences in motion sequences preserving affine structure
per: Sudhir, G, et al.
Publicat: (1997) -
Moving SLAM: fully unsupervised deep learning in non-rigid scenes
per: Xu, D, et al.
Publicat: (2021) -
Curved text detection in blurred/non-blurred video/scene images
per: Xue, Minglong, et al.
Publicat: (2019) -
Local langlands correspondence in rigid families
per: Johansson, C, et al.
Publicat: (2020)