CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm

TL;DR

This paper introduces CP3, a unified framework for point cloud completion that leverages a pretrain-prompt-predict paradigm inspired by NLP prompting techniques, enhancing robustness and semantic awareness.

Contribution

It proposes a novel unified paradigm for point cloud completion, integrating self-supervised pretraining, prompting, and semantic-guided refinement, outperforming existing methods.

Findings

CP3 achieves state-of-the-art performance on benchmark datasets.

The IOI pretext task improves robustness to incomplete point clouds.

Semantic Conditional Refinement enhances the quality of completed point clouds.

Abstract

Point cloud completion aims to predict complete shape from its partial observation. Current approaches mainly consist of generation and refinement stages in a coarse-to-fine style. However, the generation stage often lacks robustness to tackle different incomplete variations, while the refinement stage blindly recovers point clouds without the semantic awareness. To tackle these challenges, we unify point cloud Completion by a generic Pretrain-Prompt-Predict paradigm, namely CP3. Inspired by prompting approaches from NLP, we creatively reinterpret point cloud generation and refinement as the prompting and predicting stages, respectively. Then, we introduce a concise self-supervised pretraining stage before prompting. It can effectively increase robustness of point cloud generation, by an Incompletion-Of-Incompletion (IOI) pretext task. Moreover, we develop a novel Semantic Conditional Refinement (SCR) network at the predicting stage. It can discriminatively modulate multi-scale refinement with the guidance of semantics. Finally, extensive experiments demonstrate that our CP3 outperforms the state-of-the-art methods with a large margin.