modelnet40

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

[CVPR 2022 Oral] Official implementation for "Surface Representation for Point Clouds"

Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

A PyTorch Implementation of Pointnet++.

PVT: Point-Voxel Transformer for 3D Deep Learning

Point Cloud Registration using Representative Overlapping Points. https://arxiv.org/abs/2107.02583.

This is the official repository of the original Point Transformer architecture.

Official GitHub repo for VecKM. A very efficient and descriptive local geometry encoder / point tokenizer / patch embedder. ICML2024.

[CVPR 2021 - Official] Rigid Subset Mix (RSMix): Regularization Strategy for Point Cloud via Rigidly Mixed Samples

Code for "Rethinking the compositionality of point clouds through regularization in the hyperbolic space" (NeurIPS 2022)

Self-supervised 3D point-cloud representations (PointNet + JEPA). 86% linear probe on ModelNet40, no labels

Point-PlaneNet: Plane kernel based convolutional neural network for point clouds analysis

NPM3D: 3D Modeling & Point Clouds (MVA 2021) - Project on "Point Transformer" by H. Zhao et al.

Point Cloud- and Voxel-based architectures for ModelNet40 3D classification

NN architectures for ModelNet40 3D classification with Voxels and PointCloud approaches

CNN que toma una imagen RGB de un objeto y genera una reconstrucción 3D como nube de puntos (N×3). Implementa un CNN baseline tipo PSGN (Point Set Generation Network): ResNet-18 como encoder y un MLP como decoder.

3D point cloud classification on ModelNet40: PointNet, DGCNN and a hybrid attention-fusion model from scratch, 85.5% test accuracy

This is an unofficial implementation of the Point Transformer paper (CLASSIFIER EXTENSION)

PointNet for 3D classification on ModelNet40 (PyTorch + torch-geometric)