Robust Real-Time Face Detection
International Journal of Computer Vision
Video Completion by Motion Field Transfer
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
| Hi-index | 0.00 |
Film is regarded as an important art form, often reflecting the culture from which it is stemmed. Films record our history, represent contemporary culture and have great artistic value. Thus, they are precious cultural assets. Unfortunately, because of aging, improper storage conditions and other reasons, old films are threaten with defects caused by decaying, dust, dirt, scratch and mold. Consequently, digital film restoration, repairing defects in films, has been recognized as an important issue by archives, content owners and film companies. This paper proposes a learning-based defect detection method and a flow-based defect repairing algorithm for greatly reducing manual efforts in film restoration. The main contributions include a novel example-based approach for defect detection and a restoration algorithm which can repair seriously damaged films.