Bi-directional 3D auto-regressive model approach to motion picture restoration

Goh, Wooi Boon; Chong, M.N.; Kalra, S.; Krishnan, Dilip

doi:10.1109/icassp.1996.545876

Cited by 17 publications

(16 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bidirectional image sequence processing is adopted here [8]. The motion vector fields are estimated using a three-level multiresolution full-search algorithm [9] on the degraded sequences.…”

Section: Resultsmentioning

confidence: 99%

On the computational aspects of Gibbs-Markov random field modeling of missing-data in image sequences

Krishnan

Chong

Kalra

1999

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Abstract-Gibbs-Markov random field (GMRF) modeling has been shown to be a robust method in the detection of missing-data in image sequences for a video restoration application. However, the maximum a posteriori probability (MAP) estimation of the GMRF model requires computationally expensive optimization algorithms in order to achieve an optimal solution. The continuous relaxation labeling (RL) is explored in this paper as an efficient approach for solving the optimization problem. The conversion of the original combinatorial optimization into a continuous RL formulation is presented. The performance of the RL formulation is analyzed and compared with that of other optimization methods such as stochastic simulated annealing, iterated conditional modes, and mean field annealing. The results show that RL holds out promise as an optimization algorithm for problems in image sequence processing.

show abstract

Section: Resultsmentioning

confidence: 99%

On the computational aspects of Gibbs-Markov random field modeling of missing-data in image sequences

Krishnan

Chong

Kalra

1999

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In video restoration applications, some robust bidirectional motion estimation techniques have been developed and are already being used [1][2][3]7]. These techniques are based mainly on block matching because of the ease of implementation.…”

Section: Motion Estimationmentioning

confidence: 99%

“…In order to detect and interpolate the blotched regions, robust motion estimation techniques with respect to additive and replacement noise must be applied [1][2][3]. A priori information on the location of the missing regions facilitates the development of efficient algorithms to interpolate the missing regions.…”

Section: Introductionmentioning

confidence: 99%

Automatic Restoration of Old Motion Picture Films Using Spatiotemporal Exemplar-Based Inpainting

Gangal

Dіzdaroğlu

2006

Advanced Concepts for Intelligent Vision Systems

View full text Add to dashboard Cite

Abstract. This paper presents a method for automatic removal of local defects such as blotches and impulse noise in old motion picture films. The method is fully automatic and includes the following steps: fuzzy prefiltering, motioncompensated blotch detection, and spatiotemporal inpainting. The fuzzy prefilter removes small defective areas such as impulse noise. Modified bidirectional motion estimation with a predictive diamond search is utilized to estimate the motion vectors. The blotches are detected by the rank-ordered-difference method. Detected missing regions are interpolated by a new exemplar-based inpainting approach that operates on three successive frames. The performance of the proposed method is demonstrated on an artificially corrupted image sequence and on a real motion picture film. The results of the experiments show that the proposed method efficiently removes flashing and still blotches and impulse noise from image sequences.

show abstract

“…Bi-directional motion estimation for image sequence interpolation was studied in [13,14,16,17,25,36,37]. In this technique, two or more sets of motion vectors are estimated (in)dependently.…”

Section: Motion Estimationmentioning

confidence: 99%

“…Therefore, robust motion estimation techniques with respect to additive and replacement noise must be used. Some multiresolution schemes [6,27,31,35,40] and bi-directional schemes [13,14,16,17,25,36,37] are widely used as a robust motion estimator in many applications. Identification of the missing data regions allows efficient algorithms to be developed to interpolate these missing regions.…”

Section: Introductionmentioning

confidence: 99%

An improved motion-compensated restoration method for damaged color motion picture films

Gangal

Kayıkçıoğlu

Dіzdaroğlu

2004

Signal Processing: Image Communication

View full text Add to dashboard Cite

Bi-directional 3D auto-regressive model approach to motion picture restoration

Cited by 17 publications

References 3 publications

On the computational aspects of Gibbs-Markov random field modeling of missing-data in image sequences

On the computational aspects of Gibbs-Markov random field modeling of missing-data in image sequences

Automatic Restoration of Old Motion Picture Films Using Spatiotemporal Exemplar-Based Inpainting

An improved motion-compensated restoration method for damaged color motion picture films

Contact Info

Product

Resources

About