SASO: Joint 3D Semantic-Instance Segmentation via Multi-scale Semantic Association and Salient Point Clustering Optimization

TL;DR

SASO introduces a joint 3D segmentation framework combining multi-scale semantic association and salient point clustering optimization, improving indoor scene understanding by addressing context and data imbalance.

Contribution

The paper presents novel modules for semantic and instance segmentation, integrating clustering into training and balancing category distribution in 3D point cloud analysis.

Findings

Outperforms state-of-the-art on benchmark datasets

Effective handling of class imbalance in indoor scenes

Improved accuracy in semantic and instance segmentation

Abstract

We propose a novel 3D point cloud segmentation framework named SASO, which jointly performs semantic and instance segmentation tasks. For semantic segmentation task, inspired by the inherent correlation among objects in spatial context, we propose a Multi-scale Semantic Association (MSA) module to explore the constructive effects of the semantic context information. For instance segmentation task, different from previous works that utilize clustering only in inference procedure, we propose a Salient Point Clustering Optimization (SPCO) module to introduce a clustering procedure into the training process and impel the network focusing on points that are difficult to be distinguished. In addition, because of the inherent structures of indoor scenes, the imbalance problem of the category distribution is rarely considered but severely limits the performance of 3D scene perception. To address this issue, we introduce an adaptive Water Filling Sampling (WFS) algorithm to balance the category distribution of training data. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods on benchmark datasets in both semantic segmentation and instance segmentation tasks.