CounterPC: Counterfactual Feature Realignment for Unsupervised Domain Adaptation on Point Clouds

To address this, we propose CounterPC, a counterfactual intervention-based framework, which formulates domain adaptation within a causal latent space, identifying category-discriminative features entangled with intra-class geometric variation confounders. Through counterfactual interventions, we generate counterfactual target samples that retain domain-specific characteristics while improving class separation, mitigating domain bias for optimal feature transfer. To achieve this, we introduce two key modules: i) Joint Distribution Alignment, which leverages 3D foundation models (3D-FMs) and a self-supervised autoregressive generative prediction task to unify feature alignment, and ii) Counterfactual Feature Realignment, which employs Optimal Transport to align category-relevant and category-irrelevant feature distributions, ensuring robust sample-level adaptation while preserving domain properties. CounterPC outperforms current methods on PointDA and GraspNetPC-10 with significant improvements.