PointMAC：用于鲁棒测试时点云补全的元学习自适应
PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion
AI总结：
针对点云补全模型在测试时难以适应新结构和传感器失真的问题，提出元学习框架PointMAC，利用MAML策略和自监督辅助目标实现无需额外监督的样本级测试时自适应，在多类数据集上达到SOTA。
摘要：
点云补全对于机器人和增强现实等安全关键应用中的鲁棒3D感知至关重要。然而，现有模型执行静态推理，并在训练期间严重依赖归纳偏置，限制了它们在测试时适应新结构模式和传感器引起失真的能力。为了解决这一限制，我们提出了PointMAC，一个用于点云补全中鲁棒测试时自适应的元学习框架。它无需额外监督即可实现特定于样本的细化。我们的方法在两个自监督辅助目标下优化补全模型，这两个目标模拟了结构和传感器级别的不完整性。基于Model-Agnostic Meta-Learning (MAML)的元辅助学习策略确保由辅助目标驱动的自适应与主要补全任务始终对齐。在推理期间，我们通过优化辅助损失来即时自适应共享编码器，同时保持解码器固定。为了进一步稳定自适应，我们引入了Adaptive $λ$-Calibration，一种用于平衡主要和辅助目标之间梯度的元学习机制。在合成、模拟和真实世界数据集上的大量实验表明，PointMAC通过单独细化每个样本以产生高质量补全，实现了最先进的结果。据我们所知，这是将元辅助测试时自适应应用于点云补全的首个工作。
英文摘要：
Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inference and rely heavily on inductive biases learned during training, limiting their ability to adapt to novel structural patterns and sensor-induced distortions at test time. To address this limitation, we propose PointMAC, a meta-learned framework for robust test-time adaptation in point cloud completion. It enables sample-specific refinement without requiring additional supervision. Our method optimizes the completion model under two self-supervised auxiliary objectives that simulate structural and sensor-level incompleteness. A meta-auxiliary learning strategy based on Model-Agnostic Meta-Learning (MAML) ensures that adaptation driven by auxiliary objectives is consistently aligned with the primary completion task. During inference, we adapt the shared encoder on-the-fly by optimizing auxiliary losses, with the decoder kept fixed. To further stabilize adaptation, we introduce Adaptive $λ$-Calibration, a meta-learned mechanism for balancing gradients between primary and auxiliary objectives. Extensive experiments on synthetic, simulated, and real-world datasets demonstrate that PointMAC achieves state-of-the-art results by refining each sample individually to produce high-quality completions. To the best of our knowledge, this is the first work to apply meta-auxiliary test-time adaptation to point cloud completion.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
