TY - GEN
T1 - SMOC-Net
T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
AU - Tan, Tao
AU - Dong, Qiulei
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Recently, self-supervised 6D object pose estimation, where synthetic images with object poses (sometimes jointly with un-annotated real images) are used for training, has attracted much attention in computer vision. Some typical works in literature employ a time-consuming differentiable renderer for object pose prediction at the training stage, so that (i) their performances on real images are generally limited due to the gap between their rendered images and real images and (ii) their training process is computationally expensive. To address the two problems, we propose a novel Network for Self-supervised Monocular Object pose estimation by utilizing the predicted Camera poses from unannotated real images, called SMOC-Net. The proposed network is explored under a knowledge distillation framework, consisting of a teacher model and a student model. The teacher model contains a backbone estimation module for initial object pose estimation, and an object pose refiner for refining the initial object poses using a geometric constraint (called relative-pose constraint) derived from relative camera poses. The student model gains knowledge for object pose estimation from the teacher model by imposing the relative-pose constraint. Thanks to the relative-pose constraint, SMOC-Net could not only narrow the domain gap between synthetic and real data but also reduce the training cost. Experimental results on two public datasets demonstrate that SMOC-Net outperforms several state-of-the-art methods by a large margin while requiring much less training time than the differentiable-renderer-based methods.
AB - Recently, self-supervised 6D object pose estimation, where synthetic images with object poses (sometimes jointly with un-annotated real images) are used for training, has attracted much attention in computer vision. Some typical works in literature employ a time-consuming differentiable renderer for object pose prediction at the training stage, so that (i) their performances on real images are generally limited due to the gap between their rendered images and real images and (ii) their training process is computationally expensive. To address the two problems, we propose a novel Network for Self-supervised Monocular Object pose estimation by utilizing the predicted Camera poses from unannotated real images, called SMOC-Net. The proposed network is explored under a knowledge distillation framework, consisting of a teacher model and a student model. The teacher model contains a backbone estimation module for initial object pose estimation, and an object pose refiner for refining the initial object poses using a geometric constraint (called relative-pose constraint) derived from relative camera poses. The student model gains knowledge for object pose estimation from the teacher model by imposing the relative-pose constraint. Thanks to the relative-pose constraint, SMOC-Net could not only narrow the domain gap between synthetic and real data but also reduce the training cost. Experimental results on two public datasets demonstrate that SMOC-Net outperforms several state-of-the-art methods by a large margin while requiring much less training time than the differentiable-renderer-based methods.
KW - 3D from single images
UR - http://www.scopus.com/inward/record.url?scp=85173921914&partnerID=8YFLogxK
U2 - 10.1109/CVPR52729.2023.02041
DO - 10.1109/CVPR52729.2023.02041
M3 - Conference contribution
AN - SCOPUS:85173921914
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 21307
EP - 21316
BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
PB - IEEE Computer Society
Y2 - 18 June 2023 through 22 June 2023
ER -