A new auto-regressive (AR) model-based algorithm for motion picture restoration

Kalra, S.; Chong, M.N.; Krishnan, Dilip

doi:10.1109/icassp.1997.595310

Cited by 14 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…First, the pixels that are detected as "distorted" pixels are weighted according to a Gaussian weighting function (GWF) [5]. Second, a set of newly estimated unbiased AR coefficients is recomputed [5]. Finally, the "distorted" pixels identified by using (1) are then removed by substituting them with the value of calculated with the new set of AR coefficients.…”

Section: Motion Picture Restoration Systemmentioning

confidence: 99%

“…The MPR system uses a Gaussian weighted, bidirectional 3-D autoregressive (B3D-AR) model [5] to alleviate the presence of noise in the old motion picture archives. The restoration process begins with the conversion of the degraded film into its digital form with the aid of a real-time video digitizer.…”

Section: Motion Picture Restoration Systemmentioning

confidence: 99%

“…The restoration process can be seen as a threefold process. First, the pixels that are detected as "distorted" pixels are weighted according to a Gaussian weighting function (GWF) [5]. Second, a set of newly estimated unbiased AR coefficients is recomputed [5].…”

Section: Motion Picture Restoration Systemmentioning

confidence: 99%

See 2 more Smart Citations

Bidirectional motion estimation via vector propagation

Kalra¹,

Chong

1998

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

A low-complexity vector propagation (VP) algorithm is introduced for the estimation of bidirectional motion vector fields in image sequences. The proposed VP algorithm exploits the strong correlation between forward and backward motion vector fields in image sequences. The performance of the VP algorithm is compared to that of a bidirectional multiresolution blockmatching (MRBM) motion estimation (ME) algorithm. Computer simulation results demonstrate that with the VP algorithm, the computational workload of the bidirectional ME is reduced by a factor of nearly 2. The robustness of the VP algorithm is extensively tested using computer generated image sequences and real movies for a motion picture restoration (MPR) system. It is shown that the VP algorithm is robust enough to be used in the computationally demanding MPR algorithm, in which the performance of the novel VP algorithm is close to that of a bidirectional MRBM ME algorithm. With this technique, other video processing systems that desire to take advantage of bidirectional motion estimation can now do so without an excessive increase in computing time.

show abstract

Section: Motion Picture Restoration Systemmentioning

confidence: 99%

Section: Motion Picture Restoration Systemmentioning

confidence: 99%

See 1 more Smart Citation

Bidirectional motion estimation via vector propagation

Kalra¹,

Chong

1998

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Model based pixel cut and paste operations from previous or next frames then followed that allowed for occlusion and uncovering. Deterministic frameworks were proposed circa 1996 [55], [56], while a Bayesian cut-and-paste method was proposed by Roosmalen et al [36] in 1999. The essence of all these ideas was to ensure that interpolated pixel data was smooth both in time and space.…”

Section: Missing Data Reconstructionmentioning

confidence: 99%

On Missing Data Treatment for Degraded Video and Film Archives: A Survey and a New Bayesian Approach

Kokaram

2004

IEEE Trans. on Image Process.

102

118

View full text Add to dashboard Cite

Abstract-Image sequence restoration has been steadily gaining in importance with the increasing prevalence of visual digital media. The demand for content increases the pressure on archives to automate their restoration activities for preservation of the cultural heritage that they hold. There are many defects that affect archived visual material and one central issue is that of Dirt and Sparkle, or "Blotches." Research in archive restoration has been conducted for more than a decade and this paper places that material in context to highlight the advances made during that time. The paper also presents a new and simpler Bayesian framework that achieves joint processing of noise, missing data, and occlusion.

show abstract

“…Gibbs-Markov random fields [24], [31][32][33][34][35][36][37]. The determination of a MRF prior allows the detection of dirt in a Bayesian framework [3], [38][39].…”

Section: B Motion-compensated Algorithmsmentioning

confidence: 99%

Detection of dirt impairments from archived film sequences: survey and evaluations

Ren¹,

Vlachos

2010

Opt. Eng

View full text Add to dashboard Cite

----Film dirt is the most commonly encountered artefacts in archive restoration applications. Since dirt usually appears as temporal impulsive event, motion-compensated interframe processing has been widely applied for its detection. However, motion-compensated prediction requires a high degree of complexity and can be unreliable when motion estimation fails. Consequently, many techniques using spatial or spatio-temporal filtering without motion have also been proposed as alternatives. In this paper, a comprehensive survey and evaluation of existing methods is presented, in which both qualitative and quantitative performances are compared in terms of accuracy, robustness and complexity. After analysing these algorithms and identifying their limitations, we conclude with guidance in choosing from these algorithms and also promising directions for future research.

show abstract

A new auto-regressive (AR) model-based algorithm for motion picture restoration

Cited by 14 publications

References 7 publications

Bidirectional motion estimation via vector propagation

Bidirectional motion estimation via vector propagation

On Missing Data Treatment for Degraded Video and Film Archives: A Survey and a New Bayesian Approach

Detection of dirt impairments from archived film sequences: survey and evaluations

Contact Info

Product

Resources

About