Accurate as-built models of offshore platforms require component-level information from dense laser scans, but point-wise annotation is costly. We present Offshore Semi Supervised Contrastive Segmentation (OSCS), a framework for drilling platform point clouds when only a few complete scenes are annotated. OSCS constructs fixed-point-count 3D nearest-neighbor crops and uses a shared hierarchical attention encoder–decoder for supervised classification and contrastive representation learning. In unlabeled scenes, retained point identities establish positive correspondences between overlapping views. Predicted classes, confidence gating, and cross-batch class-wise feature queues organize contrastive samples without converting predictions into classification targets. Experiments used the Offshore Drilling Platform Tree Dataset (ODPT), with additional evaluation on Stanford Large-Scale 3D Indoor Spaces (S3DIS). At label budgets of approximately 10% and 20% on ODPT, OSCS achieved 88.03 ± 1.06% and 89.69 ± 0.97% mean intersection over union (mIoU) across three labeled-scene selections. The corresponding mean gains over matched supervised baselines were 4.57 and 4.42 percentage points. In the original fully labeled method comparison, OSCS achieved 92.27% mIoU, 2.67 percentage points above the strongest competing result under that protocol. Under the S3DIS Area 5 evaluation protocol, OSCS achieved 70.23% mIoU after retraining on the remaining areas. OSCS provides component-wise semantic point sets from partly annotated offshore scans, supporting the preparation of geometric information for retrofit planning and onshore prefabrication.