OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding

TL;DR

This paper summarizes the first workshop challenge on open-vocabulary 3D scene understanding, highlighting datasets, evaluation methods, and top-performing approaches to advance research in this emerging field.

Contribution

It introduces a new challenge dataset and evaluation framework for open-vocabulary 3D scene understanding, fostering research and discussion in this area.

Findings

Overview of challenge dataset and tasks

Descriptions of winning methods and approaches

Evaluation methodology for open-vocabulary 3D understanding

Abstract

This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023. The goal of this workshop series is to provide a platform for exploration and discussion of open-vocabulary 3D scene understanding tasks, including but not limited to segmentation, detection and mapping. We provide an overview of the challenge hosted at the workshop, present the challenge dataset, the evaluation methodology, and brief descriptions of the winning methods. For additional details, please see https://opensun3d.github.io/index_iccv23.html.