Name
Abstract | ||
|---|---|---|
•A novel dual-cue fused network is proposed for surface normal recovering, which exploits specular highlights, shadows and interreflections appearing in local image patches, meanwhile maintaining high-frequency details.•Compared to previous multispectral photometric stereo algorithms, the proposed method requires no extra information and breaks the limitation of Lambertian surfaces.•The Dual-cue fused network outperforms existing approaches in robustness under complex illumination. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.patcog.2019.107162 | Pattern Recognition |
Keywords | DocType | Volume |
Multispectral photometric stereo,Normal estimation,Deep neural networks,Networks fusion | Journal | 100 |
Issue | ISSN | Citations |
1 | 0031-3203 | 5 |
PageRank | References | Authors |
0.46 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yakun Ju | 1 | 9 | 3.26 |
| Xinghui Dong | 2 | 14 | 5.00 |
| Yingyu Wang | 3 | 5 | 0.80 |
| Lin Qi | 4 | 27 | 8.68 |
| Junyu Dong | 5 | 99 | 23.43 |