SOURCE-LINKED INTELLIGENCE

ScaleBlind: Point Cloud Completion under Unknown Scale

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Point cloud completion aims to infer a complete 3D shape from a partial point cloud and serves as a fundamental building block for downstream tasks such as reconstruction, editing, and simulation. Despite the recent progress, existing learning-based methods often implicitly rely on access to the ground-truth shape scale (GT-scale) during both training- and testing-time normalization, assuming privileged information that is unavailable in real-world inference. This hidden assumption limits practical deployment and can lead to severe completion artifacts, e.g., over- or under-completion and nest

Read original source ↗ Open in workspace

recordType

paper

region

Global