P2P: TuningPre-trainedImageModelsforPoint CloudAnalysiswithPoint-to-PixelPrompting SupplementalMaterial

From the classification ablation results, summation is better than max-pooling and mean-pooling. After migrating them to point cloud analysis with Point-to-Pixel Prompting, we report the number of trainable parameters (Tr. Methodmax mean sum Accuracy 92.2 92.3 92.7 (b)SegmentationAblations.