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

Jingxiang Sun, Cheng Peng, Ruizhi Shao, Yuan-Chen Guo, Xiaochen Zhao +4 more
10/16/2024
cs.CV

No official code found. Best implementation: MrTornado24/DreamCraft3D_Plus (167 stars, last commit 2024-12-16).

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° 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.

View on arXivView PDF

Code Implementations(1)

[TPAMI 2025] DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model

1674Oct 17, 20241 years ago

Cite this paper

@article{sun2024dreamcraftd,
  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},
  year   = {2024},
  eprint = {2410.12928},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.12928v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.12928.svg)](https://codeofpaper.com/paper/2410.12928)

Discussion