Abstract | ||
---|---|---|
Recent years have witnessed tremendous success of single-image depth estimation. However, most of the existing approaches merely use scene descriptions of a whole image to retrieve its candidates, which may end up with undesirable depth supports for local regions. In this paper, we propose a segmentation method for single-image depth estimation based on data-driven framework. First, a per-pixel boundary spreading method is presented to improve the image segmentation and provide local regions for image retrieval. Second, a local region image retrieval is conducted to provide a powerful support for the depth estimation of each segmented part. Third, a scene similarity matrix is constructed and combined with the initial depth prior to establish the correlations across different regions for a consistent depth optimization. Experiments show that applying our method to classic data-driven methods can improve the performance of depth estimation. Besides, our results also manifest clearer depth boundaries in some local regions than the state-of-the-art methods based on deep learning framework. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.image.2020.116048 | SIGNAL PROCESSING-IMAGE COMMUNICATION |
Keywords | DocType | Volume |
Depth estimation, Image segmentation, Consistency reconstruction, Single image | Journal | 90 |
ISSN | Citations | PageRank |
0923-5965 | 0 | 0.34 |
References | Authors | |
27 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huajun Liu | 1 | 6 | 2.79 |
Dian Lei | 2 | 0 | 1.69 |
Zhu Qing | 3 | 7 | 4.87 |
Haigang Sui | 4 | 40 | 13.76 |
Huanran Zhang | 5 | 0 | 0.34 |
Ziyan Wang | 6 | 0 | 0.34 |