2008
DOI: 10.1109/icassp.2008.4517741
|View full text |Cite
|
Sign up to set email alerts
|

A robust motion estimation method using warping for video frame enlargement

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2009
2009
2009
2009

Publication Types

Select...
2

Relationship

2
0

Authors

Journals

citations
Cited by 2 publications
(3 citation statements)
references
References 5 publications
0
3
0
Order By: Relevance
“…To address this distortion, a forward and backward predictive warping algorithm was proposed recently for uncompressed video. 7 Here we extend this approach to video coding where compressed video sequences are decompressed. This situation is different because of coding losses that have occurred before the sequence is post-processed.…”
Section: Bidirectional Warping and Hierarchical Motion Selectionmentioning
confidence: 99%
See 1 more Smart Citation
“…To address this distortion, a forward and backward predictive warping algorithm was proposed recently for uncompressed video. 7 Here we extend this approach to video coding where compressed video sequences are decompressed. This situation is different because of coding losses that have occurred before the sequence is post-processed.…”
Section: Bidirectional Warping and Hierarchical Motion Selectionmentioning
confidence: 99%
“…In a recent investigation using forward-backward warping for image enlargement, it was shown that robustness could be improved significantly. 7 With this as motivation, we have developed a forward-backward warping algorithm for enhanced definition H.264/AVC video coding. By using H.264/AVC as the basic building block, we take advantage of technology that has already been well engineered.…”
Section: Introductionmentioning
confidence: 99%
“…In next stage, the enlarged frames are compared against a reference frame. In particular, a dense motion vector field is computed [7,6,8] after which an adaptive warping algorithm is applied to warp the reference frame based on the dense motion vector field associated with each interpolated frame. In the last stage, the warped algorithm is compared with the interpolated image on a pixel-by-pixel basis.…”
Section: Introductionmentioning
confidence: 99%