University of Oulu

Cai, D., Heikkilä, J., Rahtu, E. (2023). MSDA: Monocular Self-supervised Domain Adaptation for 6D Object Pose Estimation. In: Gade, R., Felsberg, M., Kämäräinen, JK. (eds) Image Analysis. SCIA 2023. Lecture Notes in Computer Science, vol 13886. Springer, Cham.

MSDA : monocular self-supervised domain adaptation for 6D object pose estimation

Saved in:
Author: Cai, Dingding1; Heikkilä, Janne2; Rahtu, Esa1
Organizations: 1Tampere University, Tampere, Finland
2University of Oulu, Oulu, Finland
Format: article
Version: accepted version
Access: embargoed
Persistent link:
Language: English
Published: Springer Nature, 2023
Publish Date: 2024-04-27


Acquiring labeled 6D poses from real images is an expensive and time-consuming task. Though massive amounts of synthetic RGB images are easy to obtain, the models trained on them suffer from noticeable performance degradation due to the synthetic-to-real domain gap. To mitigate this degradation, we propose a practical self-supervised domain adaptation approach that takes advantage of real RGB(-D) data without needing real pose labels. We first pre-train the model with synthetic RGB images and then utilize real RGB(-D) images to fine-tune the pre-trained model. The fine-tuning process is self-supervised by the RGB-based pose-aware consistency and the depth-guided object distance pseudo-label, which does not require the time-consuming online differentiable rendering. We build our domain adaptation method based on the recent pose estimator SC6D and evaluate it on the YCB-Video dataset. We experimentally demonstrate that our method achieves comparable performance against its fully-supervised counterpart while outperforming existing state-of-the-art approaches.

see all

Series: Lecture notes in computer science
ISSN: 0302-9743
ISSN-E: 1611-3349
ISSN-L: 0302-9743
ISBN: 978-3-031-31438-4
ISBN Print: 978-3-031-31437-7
Volume: 13886
Pages: 467 - 481
DOI: 10.1007/978-3-031-31438-4_31
Host publication: Image Analysis 22nd Scandinavian Conference, SCIA 2023 Sirkka, Finland, April 18–21, 2023 Proceedings, Part II
Host publication editor: Gade, Rikke
Felsberg, Michael
Kämäräinen, Joni-Kristian
Conference: Scandinavian Conference on Image Analysis
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Funding: This work was supported by the Academy of Finland under the projects #327910 and #353139.
Copyright information: © 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG.