PCDreamer：通过多视角扩散先验的点云完成
摘要
本文提出了 PCDreamer，一种用于点云完成的新方法。传统方法通常从部分点云中提取特征以预测缺失区域，但大范围的解空间常导致结果不令人满意。更近期的方法开始将图像作为额外指导，有效提升了性能，但获取图像和部分点云的配对数据在实践中具有挑战性。为克服这些限制，我们利用大型模型中相对视角一致的多视角扩散先验，生成所需形状的新视角。 resulting image set encodes both global and local shape cues, which are especially beneficial for shape completion. To fully exploit the priors, we have designed a shape fusion module for producing an initial complete shape from multi-modality input (i.e., images and point clouds), and a follow-up shape consolidation module to obtain the final complete shape by discarding unreliable points introduced by the inconsistency from diffusion priors. Extensive experimental results demonstrate our superior performance, especially in recovering fine details.
关键词
引用
@article{arxiv.2411.19036,
title = {PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors},
author = {Guangshun Wei and Yuan Feng and Long Ma and Chen Wang and Yuanfeng Zhou and Changjian Li},
journal= {arXiv preprint arXiv:2411.19036},
year = {2025}
}
备注
Project page: https://gsw-d.github.io/PCDreamer/