Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learning

2025-07-09

AI Summary

In 3D point cloud semantic segmentation, ambiguous labels in transitional regions and unreliable ground-truth annotations for boundary points hinder model performance, while existing methods lack explicit ambiguity awareness. To address this, we propose AMContrast3D++, the first adaptive boundary learning framework that embeds point-wise ambiguity estimation into contrastive learning. Its core innovations include a dual-branch architecture and a mask refinement mechanism that jointly model spatial-position-based ambiguity. Based on estimated ambiguity, the framework dynamically modulates the contrastive loss: relaxing supervision for highly ambiguous points and strengthening discriminative constraints for confident ones. This enables end-to-end ambiguity-aware training. Extensive experiments on S3DIS and ScanNet demonstrate significant improvements in both overall segmentation accuracy and boundary-region precision, alongside enhanced robustness to labeling noise and geometric ambiguities.

Technology Category

• Computer Vision: 3D Computer Vision
• Search and Optimization: Learning to Search
• Machine Learning: Semi-Supervised Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

This paper proposes an adaptive margin contrastive learning method for 3D semantic segmentation on point clouds. Most existing methods use equally penalized objectives, which ignore the per-point ambiguities and less discriminated features stemming from transition regions. However, as highly ambiguous points may be indistinguishable even for humans, their manually annotated labels are less reliable, and hard constraints over these points would lead to sub-optimal models. To address this, we first design AMContrast3D, a method comprising contrastive learning into an ambiguity estimation framework, tailored to adaptive objectives for individual points based on ambiguity levels. As a result, our method promotes model training, which ensures the correctness of low-ambiguity points while allowing mistakes for high-ambiguity points. As ambiguities are formulated based on position discrepancies across labels, optimization during inference is constrained by the assumption that all unlabeled points are uniformly unambiguous, lacking ambiguity awareness. Inspired by the insight of joint training, we further propose AMContrast3D++ integrating with two branches trained in parallel, where a novel ambiguity prediction module concurrently learns point ambiguities from generated embeddings. To this end, we design a masked refinement mechanism that leverages predicted ambiguities to enable the ambiguous embeddings to be more reliable, thereby boosting segmentation performance and enhancing robustness. Experimental results on 3D indoor scene datasets, S3DIS and ScanNet, demonstrate the effectiveness of the proposed method. Code is available at https://github.com/YangChenApril/AMContrast3D.

Problem

• Addresses ambiguity in 3D point cloud segmentation
• Adapts contrastive learning for per-point ambiguity levels
• Improves segmentation by refining ambiguous embeddings

Innovation

• Adaptive margin contrastive learning for segmentation
• Ambiguity prediction from embeddings via joint training
• Masked refinement mechanism enhances segmentation robustness