Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency
This addresses the domain shift problem in 3D computer vision for applications like robotics and AR/VR, though it appears incremental as it builds on existing view consistency ideas.
The paper tackles the problem of 3D keypoint estimation from single depth scans or images across different domains without labeled target data, achieving superior performance compared to state-of-the-art domain adaptation methods.
In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image. Our key idea is to utilize the fact that predictions from different views of the same or similar objects should be consistent with each other. Such view consistency can provide effective regularization for keypoint prediction on unlabeled instances. In addition, we introduce a geometric alignment term to regularize predictions in the target domain. The resulting loss function can be effectively optimized via alternating minimization. We demonstrate the effectiveness of our approach on real datasets and present experimental results showing that our approach is superior to state-of-the-art general-purpose domain adaptation techniques.