Efficient Part-level 3D Object Generation via Dual Volume Packing
Jiaxiang Tang, Ruijie Lu, Max Li, Zekun Hao, Xuan Li, Fangyin Wei, Shuran Song, Gang Zeng
Abstract
Recent progress in 3D object generation has greatly improved both the quality and efficiency. However, most existing methods generate a single mesh with all parts fused together, which limits the ability to edit or manipulate individual parts. A key challenge is that different objects may have a varying number of parts. To address this, we propose a new end-to-end framework for part-level 3D object generation. Given a single input image, our method generates high-quality 3D objects with an arbitrary number of complete and semantically meaningful parts. We introduce a dual volume packing strategy that organizes all parts into two complementary volumes, allowing for the creation of complete and interleaved parts that assemble into the final object. Experiments show that our model achieves better quality, diversity, and generalization than previous image-based part-level generation methods. Our project page is at \url{https://research.nvidia.com/labs/dir/partpacker/}.
BibTeX
@inproceedings{
tang2025efficient,
title={Efficient Part-level 3D Object Generation via Dual Volume Packing},
author={Jiaxiang Tang and Ruijie Lu and Max Li and Zekun Hao and Xuan Li and Fangyin Wei and Shuran Song and Gang Zeng and Ming-Yu Liu and Tsung-Yi Lin},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=qbVbZWxUib}
}