HY3D-Bench: Generation of 3D Assets

TL;DR

HY3D-Bench is an open-source ecosystem that provides a large, high-quality, and diverse dataset of 3D objects with detailed part-level annotations, designed to accelerate research and development in 3D content generation and perception.

Contribution

It introduces a comprehensive 3D asset library, part-level decomposition for detailed control, and a scalable pipeline for synthetic data generation to address data bottlenecks in 3D AI.

Findings

Validated by training Hunyuan3D-2.1-Small model

Democratizes access to large-scale 3D datasets

Enhances diversity in long-tail categories

Abstract

While recent advances in neural representations and generative models have revolutionized 3D content creation, the field remains constrained by significant data processing bottlenecks. To address this, we introduce HY3D-Bench, an open-source ecosystem designed to establish a unified, high-quality foundation for 3D generation. Our contributions are threefold: (1) We curate a library of 250k high-fidelity 3D objects distilled from large-scale repositories, employing a rigorous pipeline to deliver training-ready artifacts, including watertight meshes and multi-view renderings; (2) We introduce structured part-level decomposition, providing the granularity essential for fine-grained perception and controllable editing; and (3) We bridge real-world distribution gaps via a scalable AIGC synthesis pipeline, contributing 125k synthetic assets to enhance diversity in long-tail categories. Validated empirically through the training of Hunyuan3D-2.1-Small, HY3D-Bench democratizes access to robust data resources, aiming to catalyze innovation across 3D perception, robotics, and digital content creation.