Guided Depth Upsampling via A Cosparse Analysis Model

Xiaojin Gong, Jianqiang Ren, Baisheng Lai, Chaohua Yan, Hui Qian; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2014, pp. 724-731

Abstract


This paper proposes a new approach to upsample depth maps when aligned high-resolution color images are given. Such a task is referred to as guided depth upsampling in our work. We formulate this problem based on the recently developed sparse representation analysis models. More specifically, we exploit the cosparsity of analytic analysis operators performed on a depth map, together with data fidelity and color guided smoothness constraints for upsampling. The formulated problem is solved by the greedy analysis pursuit algorithm. Since our approach relies on the analytic operators such as the Wavelet transforms and the finite difference operators, it does not require any training data but a single depth-color image pair. A variety of experiments have been conducted on both synthetic and real data. Experimental results demonstrate that our approach outperforms the specialized state-of-the-art algorithms.

Related Material


[pdf]
[bibtex]
@InProceedings{Gong_2014_CVPR_Workshops,
author = {Gong, Xiaojin and Ren, Jianqiang and Lai, Baisheng and Yan, Chaohua and Qian, Hui},
title = {Guided Depth Upsampling via A Cosparse Analysis Model},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2014}
}