HY3D-Bench: Generation of 3D Assets
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.
Cite
@article{arxiv.2602.03907,
title = {HY3D-Bench: Generation of 3D Assets},
author = {Team Hunyuan3D and : and Bowen Zhang and Chunchao Guo and Dongyuan Guo and Haolin Liu and Hongyu Yan and Huiwen Shi and Jiaao Yu and Jiachen Xu and Jingwei Huang and Kunhong Li and Lifu Wang and Linus and Penghao Wang and Qingxiang Lin and Ruining Tang and Xianghui Yang and Yang Li and Yirui Guan and Yunfei Zhao and Yunhan Yang and Zeqiang Lai and Zhihao Liang and Zibo Zhao},
journal= {arXiv preprint arXiv:2602.03907},
year = {2026}
}
Comments
Authors are listed alphabetically by the first name