DisARM: Displacement Aware Relation Module for 3D Detection

TL;DR

DisARM introduces a relation module that selectively uses semantic-aware anchors to incorporate contextual information, significantly improving 3D detection accuracy in point cloud scenes.

Contribution

The paper proposes a novel displacement-aware relation module that efficiently utilizes representative anchors to enhance 3D object detection performance.

Findings

Achieves state-of-the-art results on SUN RGB-D and ScanNet V2 benchmarks.

Significantly improves detection accuracy when integrated with existing detectors.

Efficiently models context by focusing on semantic-aware anchors rather than all relations.

Abstract

We introduce Displacement Aware Relation Module (DisARM), a novel neural network module for enhancing the performance of 3D object detection in point cloud scenes. The core idea of our method is that contextual information is critical to tell the difference when the instance geometry is incomplete or featureless. We find that relations between proposals provide a good representation to describe the context. However, adopting relations between all the object or patch proposals for detection is inefficient, and an imbalanced combination of local and global relations brings extra noise that could mislead the training. Rather than working with all relations, we found that training with relations only between the most representative ones, or anchors, can significantly boost the detection performance. A good anchor should be semantic-aware with no ambiguity and independent with other anchors as well. To find the anchors, we first perform a preliminary relation anchor module with an objectness-aware sampling approach and then devise a displacement-based module for weighing the relation importance for better utilization of contextual information. This lightweight relation module leads to significantly higher accuracy of object instance detection when being plugged into the state-of-the-art detectors. Evaluations on the public benchmarks of real-world scenes show that our method achieves state-of-the-art performance on both SUN RGB-D and ScanNet V2.