English

DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model

Computer Vision and Pattern Recognition 2024-10-18 v1

Abstract

We introduce DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets. DreamCraft3D++ inherits the multi-stage generation process of DreamCraft3D, but replaces the time-consuming geometry sculpting optimization with a feed-forward multi-plane based reconstruction model, speeding up the process by 1000x. For texture refinement, we propose a training-free IP-Adapter module that is conditioned on the enhanced multi-view images to enhance texture and geometry consistency, providing a 4x faster alternative to DreamCraft3D's DreamBooth fine-tuning. Experiments on diverse datasets demonstrate DreamCraft3D++'s ability to generate creative 3D assets with intricate geometry and realistic 360{\deg} textures, outperforming state-of-the-art image-to-3D methods in quality and speed. The full implementation will be open-sourced to enable new possibilities in 3D content creation.

Keywords

Cite

@article{arxiv.2410.12928,
  title  = {DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model},
  author = {Jingxiang Sun and Cheng Peng and Ruizhi Shao and Yuan-Chen Guo and Xiaochen Zhao and Yangguang Li and Yanpei Cao and Bo Zhang and Yebin Liu},
  journal= {arXiv preprint arXiv:2410.12928},
  year   = {2024}
}

Comments

Project Page: https://dreamcraft3dplus.github.io/

R2 v1 2026-06-28T19:24:47.730Z