3D vision-language grounding, which focuses on aligning language with the 3D
physical environment, stands as a cornerstone in the development of embodied
agents. In comparison to recent advancements in the 2D domain, grounding
language in 3D scenes faces several significant challenges: (i) the inherent
complexity of 3D scenes due to the diverse object configurations, their rich
attributes, and intricate relationships; (ii) the scarcity of paired 3D
vision-language data to support grounded learning; and (iii) the absence of a
unified learning framework to distill knowledge from grounded 3D data. In this
work, we aim to address these three major challenges in 3D vision-language by
examining the potential of systematically upscaling 3D vision-language learning
in indoor environments. We introduce the first million-scale 3D vision-language
dataset, SceneVerse, encompassing about 68K 3D indoor scenes and comprising
2.5M vision-language pairs derived from both human annotations and our scalable
scene-graph-based generation approach. We demonstrate that this scaling allows
for a unified pre-training framework, Grounded Pre-training for Scenes (GPS),
for 3D vision-language learning. Through extensive experiments, we showcase the
effectiveness of GPS by achieving state-of-the-art performance on all existing
3D visual grounding benchmarks. The vast potential of SceneVerse and GPS is
unveiled through zero-shot transfer experiments in the challenging 3D
vision-language tasks. Project website: this https URL .

通过系统性地将 3D 视觉语言学习在室内环境中进行有序提升，本研究旨在解决 3D 视觉语言面临的三个主要挑战，包括复杂的 3D 场景、缺乏数据支持和缺乏统一的学习框架，并通过引入包含约 68K 个 3D 室内场景的场景语料库 SceneVerse 以及基于可扩展的场景图生成方法获取的约 2.5M 个视觉语言对，展示了 Grounded Pre-training for Scenes (GPS) 的有效性，通过在所有现有的 3D 视觉定位基准上取得了最先进的性能，并在具有挑战性的 3D 视觉语言任务的零样本迁移实验中揭示了 SceneVerse 和 GPS 的巨大潜力。