(b) Fig(b) Fig. 1: (a) Pipeline of MAE for 3D point cloud representation learning. (b) Empirical analysis of representative 3D MAE methods. Left: gradient ratio between positional embeddings (π) and encoder outputs (Z) during training. Right: sensitivity analysis of reconstruction error under perturbations applied to positional embeddings.这张图概括 Mitigating Positional Leakage in 3D 的整体方法流程。阅读时先看模块之间传递的训练信号,再看作者如何把目标拆成可优化的子问题。Figureure 2 · : Pipeline of MPL-MAEFig. 2: Pipeline of MPL-MAE. The RPE module generates recalibrated positional embeddings for the decoder. A GPI module is inserted before each Transformer layer in the decoder to regulate positional injection, promoting balanced optimization and robust geometric feature learning.这张图概括 Mitigating Positional Leakage in 3D 的整体方法流程。阅读时先看模块之间传递的训练信号,再看作者如何把目标拆成可优化的子问题。