shapenet

PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)

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

[NeurIPS 2019, Spotlight] Point-Voxel CNN for Efficient 3D Deep Learning

Implementation of "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images" (Xie et al., ICCV 2019)

Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation. In ICCV2019.

Torch Implementation of NIPS'16 paper: Perspective Transformer Nets

Source code for: Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds), accepted at ACCV 2018

We evaluate our method on different datasets (including ShapeNet, CUB-200-2011, and Pascal3D+) and achieve state-of-the-art results, outperforming all the other supervised and unsupervised methods and 3D representations, all in terms of performance, accuracy, and training time.

code for "Neural Cages for Detail-Preserving 3D Deformations"

(latest updates and bug fixed) DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

Official implementation of GraphX-Convolution

Graph-convolutional GAN for point cloud generation. Code from ICLR 2019 paper Learning Localized Generative Models for 3D Point Clouds via Graph Convolution

Given an image and a target viewpoint, generate synthetic image in the target viewpoint

Supplementary code for SHREC 2017 RGB-D Object-to-CAD Retrieval track

Learning Graph-Convolutional Representations for Point Cloud Denoising (ECCV 2020)

ShapeGlot: Learning Language for Shape Differentiation

PyTorch implementation to train MortonNet and use it to compute point features. MortonNet is trained in a self-supervised fashion, and the features can be used for general tasks like part or semantic segmentation of point clouds.

Rendering color and depth images for ShapeNet models.

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

CompoNET: geometric deep learning approach in architecture. From a single-image generates a building with all its components

PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features

University of Toronto CSC2547 Final Project with Ioannis Xarchakos and Varun Pandya

Pytorch Implementation of "Unsupervised Learning of Shape and Pose with Differentiable Point Clouds". ShapeNet->CNN->PointCloud->Differentiable Rendering->Backprop

Python bindings for https://github.com/hjwdzh/Manifold

Perturbation experiments on the latent capsules of 3D Point Capsule Networks by Zhao et al.