PFF-Net: Patch Feature Fitting for Point Cloud Normal Estimation

2025-11-26

AI Summary

Point cloud normal estimation faces challenges in selecting appropriate neighborhood scales and accurately representing local geometric features. To address these issues, this paper proposes a multi-scale feature fusion framework based on patch-wise feature fitting. The method employs an adaptive neighborhood-shrinking multi-scale feature aggregation module, integrated with a cross-scale feature compensation mechanism, to enable hierarchical modeling and fine-grained fitting of local geometry. Compared to single-scale approaches, it significantly improves robustness against complex curvature variations and noise corruption. Extensive experiments demonstrate state-of-the-art performance on both synthetic (e.g., PCPNet) and real-world datasets (e.g., ScanNet, KITTI). Moreover, the proposed method reduces model parameters by approximately 23% and inference latency by 18%, achieving a favorable balance among accuracy, computational efficiency, and generalization capability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Learning with Manifolds
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Estimating the normal of a point requires constructing a local patch to provide center-surrounding context, but determining the appropriate neighborhood size is difficult when dealing with different data or geometries. Existing methods commonly employ various parameter-heavy strategies to extract a full feature description from the input patch. However, they still have difficulties in accurately and efficiently predicting normals for various point clouds. In this work, we present a new idea of feature extraction for robust normal estimation of point clouds. We use the fusion of multi-scale features from different neighborhood sizes to address the issue of selecting reasonable patch sizes for various data or geometries. We seek to model a patch feature fitting (PFF) based on multi-scale features to approximate the optimal geometric description for normal estimation and implement the approximation process via multi-scale feature aggregation and cross-scale feature compensation. The feature aggregation module progressively aggregates the patch features of different scales to the center of the patch and shrinks the patch size by removing points far from the center. It not only enables the network to precisely capture the structure characteristic in a wide range, but also describes highly detailed geometries. The feature compensation module ensures the reusability of features from earlier layers of large scales and reveals associated information in different patch sizes. Our approximation strategy based on aggregating the features of multiple scales enables the model to achieve scale adaptation of varying local patches and deliver the optimal feature description. Extensive experiments demonstrate that our method achieves state-of-the-art performance on both synthetic and real-world datasets with fewer network parameters and running time.

Problem

• Determining optimal neighborhood size for point cloud normal estimation
• Addressing difficulties in accurate normal prediction across various geometries
• Achieving robust normal estimation with efficient parameter usage

Innovation

• Fuses multi-scale features from different neighborhood sizes
• Aggregates patch features progressively to the center
• Compensates cross-scale features for optimal geometric description