Title :
Video Colorization Using Parallel Optimization in Feature Space
Author :
Bin Sheng ; Hanqiu Sun ; Magnor, Marcus ; Ping Li
Author_Institution :
Dept. of Comput. Sci. & Eng., Shanghai Jiao Tong Univ., Shanghai, China
Abstract :
We present a new scheme for video colorization using optimization in rotation-aware Gabor feature space. Most current methods of video colorization incur temporal artifacts and prohibitive processing costs, while this approach is designed in a spatiotemporal manner to preserve temporal coherence. The parallel implementation on graphics hardware is also facilitated to achieve realtime performance of color optimization. By adaptively clustering video frames and extending Gabor filtering to optical flow computation, we can achieve real-time color propagation within and between frames. Temporal coherence is further refined through user scribbles in video frames. The experimental results demonstrate that our proposed approach is efficient in producing high-quality colorized videos.
Keywords :
Gabor filters; image colour analysis; optimisation; pattern clustering; video signal processing; Gabor feature space; Gabor filtering; color optimization; feature space; graphics hardware; optical flow computation; parallel optimization; real-time color propagation; realtime performance; temporal artifacts; temporal coherence; user scribbles; video colorization; video frames; video frames clustering; Coherence; Gray-scale; Image color analysis; Linear systems; Optical imaging; Optimization; Vectors; Gabor feature space; parallel optimization; user strokes; video colorization;
Journal_Title :
Circuits and Systems for Video Technology, IEEE Transactions on
DOI :
10.1109/TCSVT.2013.2276702