OpenSU3D: Open World 3D Scene Understanding using Foundation Models

TL;DR

OpenSU3D introduces a scalable, open-world 3D scene understanding method that leverages foundation models for incremental scene construction, enabling zero-shot generalization and improved handling of complex queries.

Contribution

The paper proposes a novel approach that uses 2D foundation models and large language models to build and annotate 3D scenes incrementally, overcoming scalability issues of prior methods.

Findings

Outperforms existing methods on ScanNet and Replica datasets

Demonstrates zero-shot generalization to new scenes

Effectively handles complex queries with enhanced feature fusion

Abstract

In this paper, we present a novel, scalable approach for constructing open set, instance-level 3D scene representations, advancing open world understanding of 3D environments. Existing methods require pre-constructed 3D scenes and face scalability issues due to per-point feature vector learning, limiting their efficacy with complex queries. Our method overcomes these limitations by incrementally building instance-level 3D scene representations using 2D foundation models, efficiently aggregating instance-level details such as masks, feature vectors, names, and captions. We introduce fusion schemes for feature vectors to enhance their contextual knowledge and performance on complex queries. Additionally, we explore large language models for robust automatic annotation and spatial reasoning tasks. We evaluate our proposed approach on multiple scenes from ScanNet and Replica datasets demonstrating zero-shot generalization capabilities, exceeding current state-of-the-art methods in open world 3D scene understanding.