AI Paper Atlas

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

NeurIPS 2025 · Point clouds › Shape and surface completion · approach: Structure-guided completion · 0 citations (OpenAlex)

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy