← Search

Miguel Bordallo Lopez

1 accepted papers

2025

APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction

NeurIPS 2025poster

Training deep learning models for point cloud prediction tasks such as shape completion and generation depends critically on loss functions that measure discrepancies between predicted and ground-truth point sets. Commonly used functions such as Chamfer Distance (CD), HyperCD, InfoCD and Density-awa…

Cited by 0SourcecodeScholar