RealDiff无需合成数据，直接用真实测量做点云补全。
RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models
- 将补全任务建模为基于真实数据的条件生成，利用扩散过程恢复缺失部分。
- 通过匹配预测轮廓和深度图与外部估计结果，提升对噪声数据的鲁棒性。
- 在真实场景下性能超越现有方法，适合工业扫描等实际应用。
点云补全旨在从局部观测中恢复物体的完整三维形状。尽管依赖合成形状先验的方法在此领域取得了良好效果，但其在真实世界数据上的适用性和泛化能力仍有限。为此，本文提出一种自监督框架 RealDiff，将点云补全直接建模为基于真实测量的条件生成问题。为更好处理噪声观测且不依赖合成数据训练，RealDiff引入额外几何线索。具体而言，模型在缺失部分模拟扩散过程，同时以局部输入为条件，以应对任务的多模态特性。此外，通过匹配方法预测的物体轮廓和深度图与外部估计结果，进一步正则化训练过程。实验表明，该方法在真实世界点云补全任务中持续优于当前最优方法。
原文摘要 · Abstract (English)
Point cloud completion aims to recover the complete 3D shape of an object from partial observations. While approaches relying on synthetic shape priors achieved promising results in this domain, their applicability and generalizability to real-world data are still limited. To tackle this problem, we propose a self-supervised framework, namely RealDiff, that formulates point cloud completion as a conditional generation problem directly on real-world measurements. To better deal with noisy observations without resorting to training on synthetic data, we leverage additional geometric cues. Specifically, RealDiff simulates a diffusion process at the missing object parts while conditioning the generation on the partial input to address the multimodal nature of the task. We further regularize the training by matching object silhouettes and depth maps, predicted by our method, with the externally estimated ones. Experimental results show that our method consistently outperforms state-of-the-art methods in real-world point cloud completion.
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。