OpenFusion++: An Open-vocabulary Real-time Scene Understanding System
This work improves 3D perception for applications like vision-language navigation and augmented reality, representing an incremental advancement over existing methods.
The paper tackles real-time open-vocabulary scene understanding by addressing issues like imprecise instance segmentation and static semantic updates, resulting in OpenFusion++, which significantly outperforms baselines in semantic accuracy and query responsiveness on datasets such as ICL, Replica, ScanNet, and ScanNet++.
Real-time open-vocabulary scene understanding is essential for efficient 3D perception in applications such as vision-language navigation, embodied intelligence, and augmented reality. However, existing methods suffer from imprecise instance segmentation, static semantic updates, and limited handling of complex queries. To address these issues, we present OpenFusion++, a TSDF-based real-time 3D semantic-geometric reconstruction system. Our approach refines 3D point clouds by fusing confidence maps from foundational models, dynamically updates global semantic labels via an adaptive cache based on instance area, and employs a dual-path encoding framework that integrates object attributes with environmental context for precise query responses. Experiments on the ICL, Replica, ScanNet, and ScanNet++ datasets demonstrate that OpenFusion++ significantly outperforms the baseline in both semantic accuracy and query responsiveness.