Colorization of Natural Images via L1 Optimization

Details Colorization of Natural Images via L1 Optimization Colorization of Natural Images via L1 Optimization

2009-05-18

arxiv.org/abs/0905.2924v1

Computer Science

Computer Vision and Pattern Recognition

5 pages, 3 figures

Scientific paper

Natural images in the colour space YUV have been observed to have a non-Gaussian, heavy tailed distribution (called 'sparse') when the filter G(U)(r) = U(r) - sum_{s \in N(r)} w{(Y)_{rs}} U(s), is applied to the chromacity channel U (and equivalently to V), where w is a weighting function constructed from the intensity component Y [1]. In this paper we develop Bayesian analysis of the colorization problem using the filter response as a regularization term to arrive at a non-convex optimization problem. This problem is convexified using L1 optimization which often gives the same results for sparse signals [2]. It is observed that L1 optimization, in many cases, over-performs the famous colorization algorithm by Levin et al [3].

Affiliated with

Also associated with

No associations

Rating

Colorization of Natural Images via L1 Optimization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Colorization of Natural Images via L1 Optimization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Colorization of Natural Images via L1 Optimization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-610096