OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data

6 Nov 2023  ·  Shiyang Lu, Haonan Chang, Eric Pu Jing, Abdeslam Boularias, Kostas Bekris ·

This work presents OVIR-3D, a straightforward yet effective method for open-vocabulary 3D object instance retrieval without using any 3D data for training. Given a language query, the proposed method is able to return a ranked set of 3D object instance segments based on the feature similarity of the instance and the text query. This is achieved by a multi-view fusion of text-aligned 2D region proposals into 3D space, where the 2D region proposal network could leverage 2D datasets, which are more accessible and typically larger than 3D datasets. The proposed fusion process is efficient as it can be performed in real-time for most indoor 3D scenes and does not require additional training in 3D space. Experiments on public datasets and a real robot show the effectiveness of the method and its potential for applications in robot navigation and manipulation.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Open-Vocabulary Instance Segmentation Replica OVIR-3D mAP 11.1 # 5

Methods


No methods listed for this paper. Add relevant methods here