{"ID":2843239,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.07978","arxiv_id":"2511.07978","title":"DANCE: Density-agnostic and Class-aware Network for Point Cloud Completion","abstract":"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.","short_abstract":"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 va...","url_abs":"https://arxiv.org/abs/2511.07978","url_pdf":"https://arxiv.org/pdf/2511.07978v2","authors":"[\"Da-Yeong Kim\",\"Yeong-Jun Cho\"]","published":"2025-11-11T08:45:06Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}