Open-Set 3D Semantic Instance Maps for Vision Language Navigation -- O3D-SIM

• Published in: arXiv.org
• Main Authors: Nanwani, Laksh, Gupta, Kumaraditya, Mathur, Aditya, Agrawal, Swayam, Abdul Hafez, A H, K Madhava Krishna
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 27.04.2024
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Robotics; Feature extraction; Image segmentation; Language; Natural language processing; Object recognition; Query languages; Semantics; Three dimensional models
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2404.17922

Humans excel at forming mental maps of their surroundings, equipping them to understand object relationships and navigate based on language queries. Our previous work SI Maps [1] showed that having instance-level information and the semantic understanding of an environment helps significantly improve performance for language-guided tasks. We extend this instance-level approach to 3D while increasing the pipeline's robustness and improving quantitative and qualitative results. Our method leverages foundational models for object recognition, image segmentation, and feature extraction. We propose a representation that results in a 3D point cloud map with instance-level embeddings, which bring in the semantic understanding that natural language commands can query. Quantitatively, the work improves upon the success rate of language-guided tasks. At the same time, we qualitatively observe the ability to identify instances more clearly and leverage the foundational models and language and image-aligned embeddings to identify objects that, otherwise, a closed-set approach wouldn't be able to identify.