Unsupervised Domain Adaptation for 6-DoF Pose Estimation with Contrastive Alignment and Pseudo-Label Refinement

Nidhal Eddine Chenni, Arunkumar Rathinam, Djamila Aouada

Keywords: 6DoF pose estimation, keypoint regression, unsupervised domain adaptation, contrastive learning

TL;DR: A unified keypoint-based UDA framework for 6-DoF object pose estimation that bridges the synthetic-to-real domain gap via Contrastive Alignment and Pseudo-Label Refinement.

Abstract: Unsupervised domain adaptation (UDA) enables robust transfer of knowledge from simulated to real environments while exploiting a subset of unlabeled target data to improve real-world performance. Existing UDA methods for 6-DoF object pose estimation often rely on global feature matching, multi-stage larger frameworks, or image translation pipelines, which tend to overlook the pose-specific information embedded in feature representations. To bridge this limitation, we introduce CAPLR that targets the adaptation of pose-sensitive features in localized regions, ensuring that domain alignment preserves the geometric cues essential for accurate pose estimation. CAPLR achieves UDA with three key components: (1) Efficient Cross-Domain Pairing strategy leveraging intermediate features to identify pose similar image pairs across domains without supervision; (2) Contrastive Alignment to perform feature alignment at localised regions in both intermediate and task-specific representations; and (3) Consistency-Based Pseudo-Label Refinement to improve reliability by encouraging stable target predictions. Extensive experiments demonstrate that CAPLR achieves state-of-the-art performance across multiple well-known 6-DoF object pose estimation benchmarks featuring diverse and challenging scenarios.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 7392