DualNet: Robust Self-Supervised Stereo Matching with Pseudo-Label Supervision
Yun Wang, Jiahao Zheng, Chenghao Zhang, Zhanjie Zhang, Kunhong Li, Yongjian Zhang, Junjie Hu
Abstract
Self-supervised stereo matching has drawn attention due to its ability to estimate disparity without needing ground-truth data. However, existing self-supervised stereo matching methods heavily rely on the photo-metric consistency assumption, which is vulnerable to natural disturbances, resulting in ambiguous supervision and inferior performance compared to the supervised ones. To relax the limitation of the photo-metric consistency assumption and even bypass this assumption, we propose a novel self-supervised framework named DualNet, which consists of two key steps: robust self-supervised teacher learning and pseudo-label supervised student training. Specifically, the teacher model is first trained in a self-supervised manner with a focus on feature-metric consistency and data augmentation consistency. Then, the output of the teacher model is geometrically constrained to obtain high-quality pseudo labels. Benefiting from these high-quality pseudo labels, the student model can outperform its teacher model by a large margin. With the two well-designed steps, the proposed framework DualNet ranks 1st among all self-supervised methods on multiple benchmarks, surprisingly even outperforming several supervised counterparts.
BibTeX
@article{Wang_Zheng_Zhang_Zhang_Li_Zhang_Hu_2025, title={DualNet: Robust Self-Supervised Stereo Matching with Pseudo-Label Supervision}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32882}, DOI={10.1609/aaai.v39i8.32882}, abstractNote={Self-supervised stereo matching has drawn attention due to its ability to estimate disparity without needing ground-truth data.
However, existing self-supervised stereo matching methods heavily rely on the photo-metric consistency assumption, which is vulnerable to natural disturbances, resulting in ambiguous supervision and inferior performance compared to the supervised ones.
To relax the limitation of the photo-metric consistency assumption and even bypass this assumption, we propose a novel self-supervised framework named DualNet, which consists of two key steps: robust self-supervised teacher learning and pseudo-label supervised student training.
Specifically, the teacher model is first trained in a self-supervised manner with a focus on feature-metric consistency and data augmentation consistency.
Then, the output of the teacher model is geometrically constrained to obtain high-quality pseudo labels. Benefiting from these high-quality pseudo labels, the student model can outperform its teacher model by a large margin.
With the two well-designed steps, the proposed framework DualNet ranks 1st among all self-supervised methods on multiple benchmarks, surprisingly even outperforming several supervised counterparts.}, number={8}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wang, Yun and Zheng, Jiahao and Zhang, Chenghao and Zhang, Zhanjie and Li, Kunhong and Zhang, Yongjian and Hu, Junjie}, year={2025}, month={Apr.}, pages={8178-8186} }