Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion

TL;DR

This paper introduces a novel method for semantic segmentation of large-scale real-world point cloud data, utilizing bilateral augmentation and adaptive fusion to improve accuracy and reduce ambiguity.

Contribution

The work proposes a bilateral augmentation structure and adaptive fusion approach for enhanced semantic segmentation of real point cloud scenes, validated through extensive experiments.

Findings

Outperforms state-of-the-art methods on three benchmarks.

Effective reduction of local ambiguity in point features.

Improved segmentation accuracy demonstrated through ablation studies.

Abstract

Given the prominence of current 3D sensors, a fine-grained analysis on the basic point cloud data is worthy of further investigation. Particularly, real point cloud scenes can intuitively capture complex surroundings in the real world, but due to 3D data's raw nature, it is very challenging for machine perception. In this work, we concentrate on the essential visual task, semantic segmentation, for large-scale point cloud data collected in reality. On the one hand, to reduce the ambiguity in nearby points, we augment their local context by fully utilizing both geometric and semantic features in a bilateral structure. On the other hand, we comprehensively interpret the distinctness of the points from multiple resolutions and represent the feature map following an adaptive fusion method at point-level for accurate semantic segmentation. Further, we provide specific ablation studies and intuitive visualizations to validate our key modules. By comparing with state-of-the-art networks on three different benchmarks, we demonstrate the effectiveness of our network.