Objaverse: A Universe of Annotated 3D Objects

TL;DR

Objaverse is a large, diverse dataset of over 800,000 annotated 3D models designed to advance AI research in 3D vision and applications, filling a significant gap in existing datasets.

Contribution

The paper introduces Objaverse 1.0, a comprehensive 3D object dataset that surpasses existing repositories in scale, diversity, and annotations, enabling new AI research directions.

Findings

Facilitates training of generative 3D models

Improves tail category segmentation on LVIS benchmark

Enables open-vocabulary object-navigation in Embodied AI

Abstract

Massive data corpora like WebText, Wikipedia, Conceptual Captions, WebImageText, and LAION have propelled recent dramatic progress in AI. Large neural models trained on such datasets produce impressive results and top many of today's benchmarks. A notable omission within this family of large-scale datasets is 3D data. Despite considerable interest and potential applications in 3D vision, datasets of high-fidelity 3D models continue to be mid-sized with limited diversity of object categories. Addressing this gap, we present Objaverse 1.0, a large dataset of objects with 800K+ (and growing) 3D models with descriptive captions, tags, and animations. Objaverse improves upon present day 3D repositories in terms of scale, number of categories, and in the visual diversity of instances within a category. We demonstrate the large potential of Objaverse via four diverse applications: training generative 3D models, improving tail category segmentation on the LVIS benchmark, training open-vocabulary object-navigation models for Embodied AI, and creating a new benchmark for robustness analysis of vision models. Objaverse can open new directions for research and enable new applications across the field of AI.