3DRM:Pair-wise relation module for 3D object detection

TL;DR

This paper introduces a novel 3D relation module (3DRM) that reasons about pair-wise object relations to improve 3D object detection accuracy and robustness in scene understanding.

Contribution

The paper proposes the 3DRM, a new module for pair-wise object relation reasoning, enhancing 3D detection performance beyond existing holistic or template-based methods.

Findings

3DRM improves detection accuracy in various pipelines.

The module generalizes well across different 3D detection frameworks.

Extensive evaluations confirm the effectiveness of 3DRM.

Abstract

Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding. Existing deep contextual models either learn holistic features for context encoding or rely on pre-defined scene templates for context modeling. We argue that scene understanding benefits from object relation reasoning, which is capable of mitigating the ambiguity of 3D object detections and thus helps locate and classify the 3D objects more accurately and robustly. To achieve this, we propose a novel 3D relation module (3DRM) which reasons about object relations at pair-wise levels. The 3DRM predicts the semantic and spatial relationships between objects and extracts the object-wise relation features. We demonstrate the effects of 3DRM by plugging it into proposal-based and voting-based 3D object detection pipelines, respectively. Extensive evaluations show the effectiveness and generalization of 3DRM on 3D object detection. Our source code is available at https://github.com/lanlan96/3DRM.