OccuSeg: Occupancy-aware 3D Instance Segmentation

TL;DR

OccuSeg introduces an occupancy-aware approach for 3D instance segmentation that leverages voxel occupancy sizes to improve clustering accuracy and robustness, achieving state-of-the-art results on multiple datasets.

Contribution

The paper proposes a novel occupancy-aware 3D instance segmentation method that uses multi-task learning and size-aware clustering to enhance segmentation accuracy.

Findings

Achieves state-of-the-art performance on ScanNetV2, S3DIS, and SceneNN datasets.

Effectively balances robustness and efficiency in 3D segmentation.

Utilizes occupancy size comparison to improve clustering of hard samples.

Abstract

3D instance segmentation, with a variety of applications in robotics and augmented reality, is in large demands these days. Unlike 2D images that are projective observations of the environment, 3D models provide metric reconstruction of the scenes without occlusion or scale ambiguity. In this paper, we define "3D occupancy size", as the number of voxels occupied by each instance. It owns advantages of robustness in prediction, on which basis, OccuSeg, an occupancy-aware 3D instance segmentation scheme is proposed. Our multi-task learning produces both occupancy signal and embedding representations, where the training of spatial and feature embeddings varies with their difference in scale-aware. Our clustering scheme benefits from the reliable comparison between the predicted occupancy size and the clustered occupancy size, which encourages hard samples being correctly clustered and avoids over segmentation. The proposed approach achieves state-of-the-art performance on 3 real-world datasets, i.e. ScanNetV2, S3DIS and SceneNN, while maintaining high efficiency.