Abstract
as large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the art
face recognition by over 10%. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world face
recognition problem.
| Original language | English |
|---|---|
| Title of host publication | International Conference on Computer Vision and Pattern Recognition |
| Place of Publication | United States |
| Publisher | IEEE, Institute of Electrical and Electronics Engineers |
| Pages | 1896-1905 |
| Number of pages | 9 |
| Publication status | Published - Jun 2018 |
| Event | IEEE Conference on Computer Vision and Pattern Recognition 2018 - Calvin L. Rampton Salt Palace Convention Center, Salt Lake City, United States Duration: 18 Jun 2018 → 22 Jun 2018 |
Conference
| Conference | IEEE Conference on Computer Vision and Pattern Recognition 2018 |
|---|---|
| Abbreviated title | CVPR 2018 |
| Country | United States |
| City | Salt Lake City |
| Period | 18/06/18 → 22/06/18 |
Fingerprint
Cite this
}
Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition. / Gilani, Syed; Mian, Ajmal.
International Conference on Computer Vision and Pattern Recognition. United States : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 1896-1905.Research output: Chapter in Book/Conference paper › Conference paper
TY - GEN
T1 - Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition
AU - Gilani, Syed
AU - Mian, Ajmal
PY - 2018/6
Y1 - 2018/6
N2 - Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as wellas large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the artface recognition by over 10%. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world facerecognition problem.
AB - Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as wellas large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the artface recognition by over 10%. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world facerecognition problem.
UR - http://openaccess.thecvf.com/CVPR2018.py
UR - http://cvpr2018.thecvf.com/organizers
M3 - Conference paper
SP - 1896
EP - 1905
BT - International Conference on Computer Vision and Pattern Recognition
PB - IEEE, Institute of Electrical and Electronics Engineers
CY - United States
ER -