3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment

TL;DR

This paper introduces a weakly-supervised method for 3D visual grounding that leverages category and instance-level alignment to improve localization accuracy in point clouds without requiring detailed annotations.

Contribution

It proposes a novel approach combining category knowledge and spatial relationships to address ambiguity and complexity in 3D grounding tasks.

Findings

Achieves state-of-the-art results on Nr3D, Sr3D, and ScanRef benchmarks.

Effectively differentiates object categories and instances without detailed supervision.

Enhances 3D grounding accuracy using external detectors and language cues.

Abstract

The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges: category-level ambiguity and instance-level complexity. Category-level ambiguity arises from representing objects of fine-grained categories in a highly sparse point cloud format, making category distinction challenging. Instance-level complexity stems from multiple instances of the same category coexisting in a scene, leading to distractions during grounding. To address these challenges, we propose a novel weakly-supervised grounding approach that explicitly differentiates between categories and instances. In the category-level branch, we utilize extensive category knowledge from a pre-trained external detector to align object proposal features with sentence-level category features, thereby enhancing category awareness. In the instance-level branch, we utilize spatial relationship descriptions from language queries to refine object proposal features, ensuring clear differentiation among objects. These designs enable our model to accurately identify target-category objects while distinguishing instances within the same category. Compared to previous methods, our approach achieves state-of-the-art performance on three widely used benchmarks: Nr3D, Sr3D, and ScanRef.