PointNeXt: Revisiting PointNet+ + with 1 Improved Training and Scaling Strategies 2 -- Supplementary Material -- 3 In this appendix, we provide additional content to complement the main manuscript: 4

Appendix A: A detailed description of Tab. 7. Appendix B: Comparisons of training strategies for prior representative works and PointNeXt. We provide qualitative results of PointNeXt-XL for S3DIS (Fig. II) and PointNeXt-S ( As illustrated in Fig. I, the classification architecture shares the same encoder as the segmentation The output features of the encoder are passed to a global pooling layer ( i.e . We do not see an immediate negative societal impact from our work.