P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting Supplemental Material Ziyi Wang Xumin Y u Y ongming Rao Jie Zhou Jiwen Lu

During the geometry-preserved projection, several points may fall in the same pixel. Here we conduct ablations on the pooling strategy in Table 3, including max-pooling, mean-pooling and summation. 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. We choose 4 segments of ϕ .