Title :
Matte-Based Restoration of Vintage Video
Author :
Gai, Jiading ; Kang, Sing Bing
Author_Institution :
Dept. of Electr. Eng., Univ. of Notre Dame, South Bend, IN, USA
Abstract :
In this paper, we describe a new method for restoring digitized vintage video with film wear artifacts. Such artifacts result in partially or completely missing information. To maximize use of observed data, we cast the problem as that of recovering mattes of artifacts. More specifically, we extract the distributions of artifact color and its fractional (alpha) contribution to the frame. To account for spatial color discontinuity and pixel occlusion or disocclusion, we introduce the alpha-modulated bilateral filter. The problem is solved as a 3-D spatio-temporal conditional random field (CRF) with artifact color and (discretized) alpha as states. Inference is done through belief propagation. Results verify the effectiveness of our method. Furthermore, we can produce a synthetically generated vintage footage using extracted artifact information from actual vintage video.
Keywords :
filtering theory; hidden feature removal; image colour analysis; image restoration; video signal processing; 3D spatio-temporal conditional random field; alpha-modulated bilateral filter; film wear artifacts; matte-based restoration; pixel occlusion; spatial color discontinuity; vintage video; Artifact removal; belief propagation; bilateral filter; conditional random field; matting and compositing; video restoration; Algorithms; Artifacts; Artificial Intelligence; Image Enhancement; Image Interpretation, Computer-Assisted; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique; Video Recording;
Journal_Title :
Image Processing, IEEE Transactions on
DOI :
10.1109/TIP.2009.2025804