ptrnn

vonenet

Repository for VOneNet models

UnsupervisedPointCloudReconstruction

Experiments on unsupervised point cloud reconstruction.

capnet

Code release for "CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision", (AAAI-19)

meshrcnn

code for Mesh R-CNN, ICCV 2019

ShapenetRender_more_variation

A new shapenet rendering 2D image dataset that also contains deph map, normal map and albedo map.

PCT

Jittor implementation of PCT:Point Cloud Transformer

galerkin-transformer

[NeurIPS 2021] Galerkin Transformer: a linear attention without softmax

DeepSDF

Learning Continuous Signed Distance Functions for Shape Representation

PU-GCN

[CVPR'21] PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks

dti-sprites

(ICCV 2021) Code for "Unsupervised Layered Image Decomposition into Object Prototypes" paper

energy-based-model

TopographicVAE

Official implementation of the paper "Topographic VAEs learn Equivariant Capsules"

extension-cpp

C++ extensions in PyTorch

AtlasNet

This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity) from a low-resolution point cloud, or from an image.

awesome-long-tail-learning

2dimageto3dmodel

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.

SoftRas

Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"

tsne-cuda

GPU Accelerated t-SNE for CUDA with Python bindings

LAP-solvers

Benchmarking Linear Assignment Problem Solvers

USIP

USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds. ICCV 2019

differentiable-point-clouds

The reference implementation of "Unsupervised Learning of Shape and Pose with Differentiable Point Clouds"

PRTR

(CVPR 2021) PRTR: Pose Recognition with Cascade Transformers

LETR

(CVPR 2021 Oral) LETR: Line Segment Detection Using Transformers without Edges

3detr

Code & Models for 3DETR - an End-to-end transformer model for 3D object detection

releasing-research-code

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

PoinTr

[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

CompNet

Code of paper "Compositionally Generalizable 3D Structure Prediction"

Guided-VAE

(CVPR 2020) Guided-VAE: Guided Variational Autoencoder for Disentanglement Learning

HungarianGPU

An GPU/CUDA implementation of the Hungarian algorithm

GNM

Official Release of NeurIPS 2020 Spotlight paper "Generative Neurosymbolic Machines"