Language-Assisted 3D Feature Learning for Semantic Scene Understanding

TL;DR

This paper introduces a novel language-assisted training approach for 3D scene understanding that leverages textual descriptions to improve 3D feature learning, especially in label-scarce scenarios, and enhances multimodal task performance.

Contribution

It proposes a method to incorporate textual scene descriptions into 3D feature learning via auxiliary tasks, improving semantic understanding and multimodal alignment.

Findings

Enhanced 3D semantic scene understanding performance.

Better alignment between 3D features and language features.

Effective in label-deficient regimes.

Abstract

Learning descriptive 3D features is crucial for understanding 3D scenes with diverse objects and complex structures. However, it is usually unknown whether important geometric attributes and scene context obtain enough emphasis in an end-to-end trained 3D scene understanding network. To guide 3D feature learning toward important geometric attributes and scene context, we explore the help of textual scene descriptions. Given some free-form descriptions paired with 3D scenes, we extract the knowledge regarding the object relationships and object attributes. We then inject the knowledge to 3D feature learning through three classification-based auxiliary tasks. This language-assisted training can be combined with modern object detection and instance segmentation methods to promote 3D semantic scene understanding, especially in a label-deficient regime. Moreover, the 3D feature learned with language assistance is better aligned with the language features, which can benefit various 3D-language multimodal tasks. Experiments on several benchmarks of 3D-only and 3D-language tasks demonstrate the effectiveness of our language-assisted 3D feature learning. Code is available at https://github.com/Asterisci/Language-Assisted-3D.