DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model
This addresses the efficiency bottleneck in 3D content creation for applications like gaming and VR, though it builds incrementally on DreamCraft3D.
The paper tackles the problem of slow 3D asset generation by introducing DreamCraft3D++, which replaces optimization-based geometry sculpting with a feed-forward multi-plane reconstruction model, achieving 1000x speedup and outperforming state-of-the-art methods in quality and speed.
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.