论文标题
cp3：统一点云完成，预处理预测范式
CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm
论文作者
论文摘要
点云完成旨在从部分观察结果中预测完整的形状。当前的方法主要包括以粗到精细的方式组成的生成和完善阶段。但是，一代阶段通常缺乏解决不同不完整变化的强大性，而精致阶段则盲目地恢复了没有语义意识的点云。为了应对这些挑战，我们通过通用预处理预测的范式（即cp3）来统一点云完成。受NLP提示方法的启发，我们创造性地重新解释了点云的生成和精炼，分别为提示和预测阶段。然后，在提示之前，我们引入了一个简洁的自我监督预定阶段。通过不完整（IOI）借口任务，它可以有效地提高点云生成的鲁棒性。此外，我们在预测阶段开发了一种新颖的语义条件细化（SCR）网络。它可以通过语义的指导来区分调节多尺度改进。最后，广泛的实验表明，我们的CP3优于较大边缘的最先进方法。
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.
