Joint Geodesic Upsampling of Depth Images

Ming-Yu Liu, Oncel Tuzel, Yuichi Taguchi; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 169-176


We propose an algorithm utilizing geodesic distances to upsample a low resolution depth image using a registered high resolution color image. Specifically, it computes depth for each pixel in the high resolution image using geodesic paths to the pixels whose depths are known from the low resolution one. Though this is closely related to the all-pairshortest-path problem which has O(n lalog n) complexity, we develop a novel approximation algorithm whose complexity grows linearly with the image size and achieve realtime performance. We compare our algorithm with the state of the art on the benchmark dataset and show that our approach provides more accurate depth upsampling with fewer artifacts. In addition, we show that the proposed algorithm is well suited for upsampling depth images using binary edge maps, an important sensor fusion application.

Related Material

author = {Liu, Ming-Yu and Tuzel, Oncel and Taguchi, Yuichi},
title = {Joint Geodesic Upsampling of Depth Images},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}