UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation

TL;DR

This paper introduces UDA-COPE, an unsupervised domain adaptation approach for category-level object pose estimation that eliminates the need for ground-truth labels in the target domain, using a teacher-student self-supervised framework.

Contribution

The paper proposes a novel unsupervised domain adaptation method for object pose estimation that leverages a bidirectional filtering technique and a self-supervised learning scheme, reducing reliance on labeled data.

Findings

Achieves comparable or superior performance to label-dependent methods.

Effectively adapts to target domain without ground-truth labels.

Demonstrates robustness and reliability through extensive experiments.

Abstract

Learning to estimate object pose often requires ground-truth (GT) labels, such as CAD model and absolute-scale object pose, which is expensive and laborious to obtain in the real world. To tackle this problem, we propose an unsupervised domain adaptation (UDA) for category-level object pose estimation, called UDA-COPE. Inspired by recent multi-modal UDA techniques, the proposed method exploits a teacher-student self-supervised learning scheme to train a pose estimation network without using target domain pose labels. We also introduce a bidirectional filtering method between the predicted normalized object coordinate space (NOCS) map and observed point cloud, to not only make our teacher network more robust to the target domain but also to provide more reliable pseudo labels for the student network training. Extensive experimental results demonstrate the effectiveness of our proposed method both quantitatively and qualitatively. Notably, without leveraging target-domain GT labels, our proposed method achieved comparable or sometimes superior performance to existing methods that depend on the GT labels.