2009 IEEE 12th International Conference on Computer Vision 2009
DOI: 10.1109/iccv.2009.5459364
|View full text |Cite
|
Sign up to set email alerts
|

Large displacement optical flow computation withoutwarping

Abstract: We

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

1
79
0

Year Published

2011
2011
2023
2023

Publication Types

Select...
5
3
1

Relationship

1
8

Authors

Journals

citations
Cited by 102 publications
(80 citation statements)
references
References 11 publications
1
79
0
Order By: Relevance
“…The functions u and v are coupled by the term 1 2θ (u − v) 2 . This decoupling approach allows for an efficient GPU implementation and has been used in many related problems [22,17,14].…”
Section: Minimizationmentioning
confidence: 99%
“…The functions u and v are coupled by the term 1 2θ (u − v) 2 . This decoupling approach allows for an efficient GPU implementation and has been used in many related problems [22,17,14].…”
Section: Minimizationmentioning
confidence: 99%
“…As stated in (22), the space H div (R 2 ) corresponds to the curl of H 1 (R 2 ) scalar potential. Then, taking the curl of any multiresolution analysis of H 1 (R 2 ) will provide a multiresolution analysis of H div (R 2 ).…”
Section: Divergence-free Wavelet Basismentioning
confidence: 99%
“…Dealing with non-linearities and the multi-scale structure of motion is particularly challenging for the estimation of deformation fields generated by physical processes. Gaussian multiresolution frameworks [1] or combined integrated/variational formulations [22] have been proposed to circumvent non-linearity and achieve long range displacement estimation from consecutive images. However, the former solutions suffer from a non nested minimization formulation that may impact estimation accuracy, while the latter provide poor results for non-textured images such as images visualizing the transport of a passive scalar.…”
mentioning
confidence: 99%
“…Traditional methods handle small motion while recent development in this field begins to tackle the more challenging large-displacement estimation problem [1][2][3][4][5]. These effective methods, however, still do not consider large and non-uniform scale variation, which is ubiquitous when images are sparsely captured or objects quickly move towards or away from the camera.…”
Section: Introductionmentioning
confidence: 99%