3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding

TL;DR

This paper introduces 3DRP-Net, a novel 3D visual grounding framework that leverages relative spatial relationships and a multi-head attention mechanism to improve localization accuracy in point clouds.

Contribution

The work proposes a relation-aware one-stage network with a 3D relative position attention module and a soft-labeling strategy, advancing 3D visual grounding methods.

Findings

Outperforms state-of-the-art on ScanRefer, Nr3D, and Sr3D benchmarks.

Effectively captures relative spatial relations between objects.

Enhances learning stability through a novel soft-labeling strategy.

Abstract

3D visual grounding aims to localize the target object in a 3D point cloud by a free-form language description. Typically, the sentences describing the target object tend to provide information about its relative relation between other objects and its position within the whole scene. In this work, we propose a relation-aware one-stage framework, named 3D Relative Position-aware Network (3DRP-Net), which can effectively capture the relative spatial relationships between objects and enhance object attributes. Specifically, 1) we propose a 3D Relative Position Multi-head Attention (3DRP-MA) module to analyze relative relations from different directions in the context of object pairs, which helps the model to focus on the specific object relations mentioned in the sentence. 2) We designed a soft-labeling strategy to alleviate the spatial ambiguity caused by redundant points, which further stabilizes and enhances the learning process through a constant and discriminative distribution. Extensive experiments conducted on three benchmarks (i.e., ScanRefer and Nr3D/Sr3D) demonstrate that our method outperforms all the state-of-the-art methods in general. The source code will be released on GitHub.