Laplacian Eigenmaps for dimensionality reduction and data representation
Neural Computation
Learning a Classification Model for Segmentation
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Colorization using optimization
ACM SIGGRAPH 2004 Papers
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples
The Journal of Machine Learning Research
Novel inverse colorization for image compression
PCS'09 Proceedings of the 27th conference on Picture Coding Symposium
Learning-based multiview video coding
PCS'09 Proceedings of the 27th conference on Picture Coding Symposium
A novel customized recompression framework for massive internet images
CVM'12 Proceedings of the First international conference on Computational Visual Media
| Hi-index | 0.00 |
We present an intuitive scheme for lossy color-image compression: Use the color information from a few representative pixels to learn a model which predicts color on the rest of the pixels. Now, storing the representative pixels and the image in grayscale suffice to recover the original image. A similar scheme is also applicable for compressing videos, where a single model can be used to predict color on many consecutive frames, leading to better compression. Existing algorithms for colorization -- the process of adding color to a grayscale image or video sequence -- are tedious, and require intensive human-intervention. We bypass these limitations by using a graph-based inductive semi-supervised learning module for colorization, and a simple active learning strategy to choose the representative pixels. Experiments on a wide variety of images and video sequences demonstrate the efficacy of our algorithm.