![]() In addition, we construct a benchmark dataset captured by Kinect-v2 to facilitate research on real-world depth map SR. Quantitative and qualitative evaluations on various datasets with different magnification factors demonstrate the effectiveness and promising performance of the proposed method. The weight sharing module extracts the general features in different levels, while the adaptive module transfers the general features to the specific features to adapt to different degraded inputs. ![]() The SR subnetwork is a disentangling cascaded network to progressively upsample SR result, where every level is made up of a weight sharing module and an adaptive module. The edge prediction subnetwork takes advantage of the hierarchical representation of color and depth images to produce accurate edge maps, which promote the performance of SR subnetwork. In this paper, we propose a deep edge map guided depth SR method, which includes an edge prediction subnetwork and an SR subnetwork. However, it is difficult to predict accurate edge maps from low resolution (LR) depth maps. Therefore, many traditional SR methods utilize edge maps to guide depth SR. The edge-directed property of covariance-based adaptation attributes to its capability of tuning the interpolation coefficients to match an arbitrarily oriented step edge. Accurate edge reconstruction is critical for depth map super resolution (SR). ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |