OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding
It provides a platform for researchers to tackle open-vocabulary 3D scene understanding, but is incremental as it focuses on organizing a workshop challenge.
The paper describes the OpenSUN3D workshop challenge at ICCV 2023, which aimed to advance open-vocabulary 3D scene understanding tasks like segmentation and detection, by presenting the dataset, evaluation methods, and winning approaches.
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.