PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

(ICCV 2023) official repository for "Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation"

Point Transformers

[ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection

[ICLR 2022 poster] Official PyTorch implementation of "Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework"

[NeurIPS 2024] PointMamba: A Simple State Space Model for Point Cloud Analysis

[ICLR 2025] Point-SAM: Promptable 3D Segmentation Model for Point Clouds

Only implemented through torch: "bi - mamba2" , "vision- mamba2 -torch". support 1d/2d/3d/nd and support export by jit.script/onnx;

(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

The official implementation of DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis

(TPAMI 2023) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer

Point Cloud Mamba: Point Cloud Learning via State Space Model

Point Mamba

[ECCV 2022] Official pytorch implementation of the paper, "PointMixer: MLP-Mixer for Point Cloud Understanding"

Using Kolmogorov Arnold Networks (KANs) instead of MLPs in PointNet for Classification and Segmentation of 3D Point Sets

基于Mamba模块的图像超分任务