OpenLex3D: A Tiered Benchmark for Open-Vocabulary 3D Scene Representations

Christina Kassab, Sacha Morin, Martin Büchner, Matias Mattamala, Kumaraditya Gupta, Abhinav Valada, Liam Paull, Maurice Fallon

Keywords: Benchmarks, Open-Vocabulary Evaluation, 3D Scene Representations, Instance Retrieval, Instance Segmentation

TL;DR: We present OpenLex3D, a new benchmark for evaluating 3D open-vocabulary representations which captures real-world linguistic variability, and provides insights on feature precision, segmentation and downstream capabilities.

Abstract: 3D scene understanding has been transformed by open-vocabulary language models that enable interaction via natural language. However, at present the evaluation of these representations is limited to datasets with closed-set semantics that do not capture the richness of language. This work presents OpenLex3D, a dedicated benchmark for evaluating 3D open-vocabulary scene representations. OpenLex3D provides entirely new label annotations for scenes from Replica, ScanNet++, and HM3D, which capture real-world linguistic variability by introducing synonymical object categories and additional nuanced descriptions. Our label sets provide 13 times more labels per scene than the original datasets. By introducing an open-set 3D semantic segmentation task and an object retrieval task, we evaluate various existing 3D open-vocabulary methods on OpenLex3D, showcasing failure cases, and avenues for improvement. Our experiments provide insights on feature precision, segmentation, and downstream capabilities. The benchmark is publicly available at: https://openlex3d.github.io/.

Code URL: https://github.com/openlex3d/openlex3d

Primary Area: Datasets & Benchmarks for applications in computer vision

Submission Number: 2617