用鲁棒优化提升稀疏点云的SDF重建精度
Toward Robust Neural Reconstruction from Sparse Point Sets
- 基于分布鲁棒优化框架，引入不确定性区域样本增强正则化
- 无需真实标签即可稳定高效优化SDF，优于基线与当前最优方法
- 适用于噪声大、采样稀疏的3D重建场景，尤其适合实际扫描数据
我们研究从稀疏且含噪的3D点云中学习符号距离函数（SDF）这一挑战性问题。与依赖平滑先验的近期方法不同，我们的方法基于分布鲁棒优化（DRO）框架，引入一个正则化项，利用模型不确定性区域的样本以改进学习到的SDF。得益于可处理的对偶形式，该框架在缺乏真实标签监督的情况下，仍能实现SDF的稳定高效优化。通过多种合成数据和来自不同模态的真实数据评估，我们验证了该DRO学习框架在SDF重建方面优于基线方法和现有最先进方法。
原文摘要 · Abstract (English)
We consider the challenging problem of learning Signed Distance Functions (SDF) from sparse and noisy 3D point clouds. In contrast to recent methods that depend on smoothness priors, our method, rooted in a distributionally robust optimization (DRO) framework, incorporates a regularization term that leverages samples from the uncertainty regions of the model to improve the learned SDFs. Thanks to tractable dual formulations, we show that this framework enables a stable and efficient optimization of SDFs in the absence of ground truth supervision. Using a variety of synthetic and real data evaluations from different modalities, we show that our DRO based learning framework can improve SDF learning with respect to baselines and the state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。