Abstract | ||
---|---|---|
In this paper, we propose a new video frame interpolation technique by a locally-adaptive robust principal component analysis (RPCA) with weight priors. The proposed algorithm relies on two main steps: 1. the pre-processing step initializes the new frame by a simplified motion-compensated frame interpolation and assigns each pixel a confident weight based on both the difference of motion estimation and local consistency; and 2. the refinement step updates the frame by a proposed weighted robust principal component analysis (WRPCA) algorithm. Experiments demonstrate that the proposed method outperforms the state-of-the-art algorithms, both in visual quality and PSNR performance. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICASSP.2013.6637882 | ICASSP |
Keywords | Field | DocType |
weighted robust principal component analysis,video frame interpolation,interpolation,weight priors,simplified motion compensated frame interpolation,robust principal component analysis (rpca),frame interpolation,motion estimation,motion-compensated interpolation (mci),video coding,principal component analysis,robustness,psnr,sparse matrices,algorithm design and analysis | Mathematical optimization,Algorithm design,Pattern recognition,Computer science,Interpolation,Robustness (computer science),Robust principal component analysis,Residual frame,Motion interpolation,Artificial intelligence,Motion estimation,Principal component analysis | Conference |
ISSN | Citations | PageRank |
1520-6149 | 3 | 0.45 |
References | Authors | |
8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Minh Dao | 1 | 121 | 11.14 |
Yuanming Suo | 2 | 75 | 6.73 |
Sang Peter Chin | 3 | 58 | 10.72 |
T. D. Tran | 4 | 179 | 20.04 |