DANCE: Density-agnostic and Class-aware Network for Point Cloud Completion
It addresses the problem of variable sparsity and limited supervision in real-world 3D scanning for applications like robotics or AR/VR, offering a robust solution.
The paper tackles point cloud completion for incomplete 3D scans by introducing DANCE, a framework that recovers missing regions while preserving observed geometry, achieving state-of-the-art accuracy and structural consistency on benchmarks like PCN and MVP.
Point cloud completion aims to recover missing geometric structures from incomplete 3D scans, which often suffer from occlusions or limited sensor viewpoints. Existing methods typically assume fixed input/output densities or rely on image-based representations, making them less suitable for real-world scenarios with variable sparsity and limited supervision. In this paper, we introduce Density-agnostic and Class-aware Network (DANCE), a novel framework that completes only the missing regions while preserving the observed geometry. DANCE generates candidate points via ray-based sampling from multiple viewpoints. A transformer decoder then refines their positions and predicts opacity scores, which determine the validity of each point for inclusion in the final surface. To incorporate semantic guidance, a lightweight classification head is trained directly on geometric features, enabling category-consistent completion without external image supervision. Extensive experiments on the PCN and MVP benchmarks show that DANCE outperforms state-of-the-art methods in accuracy and structural consistency, while remaining robust to varying input densities and noise levels.