Research map / Point clouds / Shape and surface completion
Complete Structure Guided Point Cloud Completion via Cluster- and Instance-Level Contrastive Learning
Yang Chen, Yirun Zhou, WEIZHONG ZHANG, Cheng Jin
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a point cloud completion method guided by complete-structure priors using cluster-level and instance-level contrastive learning, reducing reliance on complete point cloud supervision.
Problem
Point cloud completion typically requires complete point clouds for supervision, which are rarely available in real-world settings; existing self-supervised methods are the focus of the attempt to remove this dependency.
Approach
Uses complete-structure guidance together with contrastive learning at both cluster and instance levels to learn completion without fully complete ground-truth point clouds.
Closest papers by meaning
- P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds (ICCV 2023 · similarity 0.92)
- Cascaded Refinement Network for Point Cloud Completion with Self-supervision (TPAMI 2021 · similarity 0.92)
- PointSea: Point Cloud Completion via Self-structure Augmentation (IJCV 2025 · similarity 0.92)
- ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling (CVPR 2023 · similarity 0.92)
- Position-Aware Guided Point Cloud Completion with CLIP Model (AAAI 2025 · similarity 0.89)
- PointAttN: You Only Need Attention for Point Cloud Completion (AAAI 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
