← Search

Xuanpeng Li

2 accepted papers

2025

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

ICCV 2025poster

Understanding real-world 3D point clouds is challenging due to domain shifts, causing geometric variations like density changes, noise, and occlusions. The key challenge is disentangling domain-invariant semantics from domain-specific geometric variations, as point clouds exhibit local inconsistency…

Cited by 0SourcePDFScholar
2025

Debiased Prototype Evolving for Point Cloud Domain Adaptation via 3D Foundation Models

ICASSP 2025accepted

Domain adaptation in point cloud data is essential for improving downstream tasks in autonomous driving, robotics, and 3D modeling. 3D Foundation models, driven by scaling laws, have significantly advanced point cloud applications by embedding rich semantic knowledge of geometric structures. However…

Cited by 0SourceScholar