We introduce π‘πžπšπ₯𝐏𝐂, a real-world paired industrial object point cloud dataset, and show how it’s fundamentally different from existing synthetic datasets, exhibiting rich topological features. We highlight the importance of integrating Persistent Homology priors into existing point cloud completion models, and present a Homology Sampler-based completion model, ππŽπ’π‡ππžπ­.