Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection

TL;DR

This paper introduces an object-level point augmentor for semi-supervised 3D object detection, focusing on local transformations to improve instance detection accuracy on point cloud data.

Contribution

The novel object-level point augmentor emphasizes object instances with local transformations, enhancing semi-supervised 3D detection performance over global augmentation methods.

Findings

OPA outperforms state-of-the-art methods on ScanNet and SUN RGB-D datasets.

Local object-level augmentation improves detection accuracy.

Extensive experiments validate the effectiveness of the proposed method.

Abstract

Semi-supervised object detection is important for 3D scene understanding because obtaining large-scale 3D bounding box annotations on point clouds is time-consuming and labor-intensive. Existing semi-supervised methods usually employ teacher-student knowledge distillation together with an augmentation strategy to leverage unlabeled point clouds. However, these methods adopt global augmentation with scene-level transformations and hence are sub-optimal for instance-level object detection. In this work, we propose an object-level point augmentor (OPA) that performs local transformations for semi-supervised 3D object detection. In this way, the resultant augmentor is derived to emphasize object instances rather than irrelevant backgrounds, making the augmented data more useful for object detector training. Extensive experiments on the ScanNet and SUN RGB-D datasets show that the proposed OPA performs favorably against the state-of-the-art methods under various experimental settings. The source code will be available at https://github.com/nomiaro/OPA.