Abstract | ||
---|---|---|
We present SfSNet, an end-to-end learning framework for producing an accurate decomposition of an unconstrained human face image into shape, reflectance and illuminance. SfSNet is designed to reflect a physical lambertian rendering model. SfSNet learns from a mixture of labeled synthetic and unlabeled real-world images. This allows the network to capture low-frequency variations from synthetic and... |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TPAMI.2020.3046915 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | DocType | Volume |
Faces,Lighting,Image reconstruction,Shape,Rendering (computer graphics),Three-dimensional displays,Training | Journal | 44 |
Issue | ISSN | Citations |
6 | 0162-8828 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Soumyadip Sengupta | 1 | 211 | 10.08 |
Daniel Lichy | 2 | 0 | 0.68 |
Angjoo Kanazawa | 3 | 272 | 10.36 |
Carlos D. Castillo | 4 | 173 | 9.48 |
David W. Jacobs | 5 | 4599 | 348.03 |