2 papers
cs.CV2026
MambaH-Fit: Rethinking Hyper-surface Fitting-based Point Cloud Normal Estimation via State Space Modelling
Weijia Wang, Yuanzhi Su, Pei-Gen Ye +1
We present MambaH-Fit, a state space modelling framework tailored for hyper-surface fitting-based point cloud normal estimation. Existing normal estimation methods often fall short…
cs.CV2025
Balanced Residual Distillation Learning for 3D Point Cloud Class-Incremental Semantic Segmentation
Yuanzhi Su, Siyuan Chen, Yuan-Gen Wang
Class-incremental learning (CIL) enables continuous learning of new classes while mitigating catastrophic forgetting of old ones. For the performance breakthrough of CIL, it is ess…