Text to Point Cloud Localization with Relation-Enhanced Transformer

TL;DR

This paper introduces a Relation-Enhanced Transformer that improves text-to-point-cloud localization by explicitly modeling relations among hints, achieving state-of-the-art results on a large dataset.

Contribution

The paper proposes a novel Relation-Enhanced Transformer with a relation-aware self-attention mechanism for improved cross-modal localization.

Findings

Outperforms previous methods on KITTI360Pose dataset

Explicit relation encoding enhances discriminability in localization

Effective in city-scale point cloud scenarios

Abstract

Automatically localizing a position based on a few natural language instructions is essential for future robots to communicate and collaborate with humans. To approach this goal, we focus on the text-to-point-cloud cross-modal localization problem. Given a textual query, it aims to identify the described location from city-scale point clouds. The task involves two challenges. 1) In city-scale point clouds, similar ambient instances may exist in several locations. Searching each location in a huge point cloud with only instances as guidance may lead to less discriminative signals and incorrect results. 2) In textual descriptions, the hints are provided separately. In this case, the relations among those hints are not explicitly described, leading to difficulties of learning relations. To overcome these two challenges, we propose a unified Relation-Enhanced Transformer (RET) to improve representation discriminability for both point cloud and natural language queries. The core of the proposed RET is a novel Relation-enhanced Self-Attention (RSA) mechanism, which explicitly encodes instance (hint)-wise relations for the two modalities. Moreover, we propose a fine-grained cross-modal matching method to further refine the location predictions in a subsequent instance-hint matching stage. Experimental results on the KITTI360Pose dataset demonstrate that our approach surpasses the previous state-of-the-art method by large margin.