216 Open source projects that are alternatives of or similar to Torchsparse

3D Heritage Online Presenter

Pytorch framework for doing deep learning on point clouds.

YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud (ECCV 2018)

Accompanying library for the Record3D iOS app (https://record3d.app/). Allows you to receive RGBD stream from iOS devices with TrueDepth camera(s).

Regularized Graph CNN for Point Cloud Segmentation

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Deep Hough Voting for 3D Object Detection in Point Clouds

[CVPR'19] JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds

Fast Plane Extraction Using Agglomerative Hierarchical Clustering (AHC)

Tooling for professional robotic development in C++ and Python with a touch of ROS, autonomous driving and aerospace.

This is the official implementation of RSNet.

Load 3MX/3MXB format LOD model files generated by Bentley ContextCapture into Unity.

CloudCompare main repository

📚 The list of vision-based SLAM / Visual Odometry open source, blogs, and papers

Neural Point-Based Graphics

A small Java-based tool for the generation of point cloud visualization datasets according to Cesium 3D Tiles.

Code for Pointwise Convolutional Neural Networks, CVPR 2018

Fast and robust algorithm to extract edges in unorganized point clouds

Python binding of 3D visualization library Pangolin

Weakly Supervised 3D Object Detection from Point Clouds (VS3D), ACM MM 2020

Bayesian Coherent Point Drift (BCPD/BCPD++); Source Code Available

Specification for streaming massive heterogeneous 3D geospatial datasets 🌎

code/webpage for the DeepMapping project

[CVPR 2021 - Oral] UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering

Keras implementation for Pointnet

Pytorch implementation of 'Graph Attention Convolution for Point Cloud Segmentation'

Render large point clouds and voxel grids with blender.

Patch-base progressive 3D Point Set Upsampling

User-friendly, commercial-grade software for processing aerial imagery. 🛩

A PyTorch implementation of Dynamic Graph CNN for Learning on Point Clouds (DGCNN)

A Laser-Camera Calibration Toolbox extending from that at http://www.cs.cmu.edu/~ranjith/lcct.html

Lightweight and Accurate Point Cloud Clustering

DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DOF Relocalization

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Create Dense Depth Map Image for Known Poisitioned Camera from Lidar Point Cloud

Cluster based segmentation of Point Cloud with PCL lib in ROS

3D point cloud datasets in HDF5 format, containing uniformly sampled 2048 points per shape.

This is a package for extrinsic calibration between a 3D LiDAR and a camera, described in paper: Improvements to Target-Based 3D LiDAR to Camera Calibration. This package is used for Cassie Blue's 3D LiDAR semantic mapping and automation.

Sample implementation of an application using KinectFusionLib

A learned sampling approach for point clouds (CVPR 2019)

Frustum PointNets for 3D Object Detection from RGB-D Data

Point cloud semantic segmentation via Deep 3D Convolutional Neural Network

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

open Multi-View Stereo reconstruction library

A small VEX raytracer for SideFX Houdini with photon mapping global illumination and full recursive reflections and refractions

Grid-GCN for Fast and Scalable Point Cloud Learning

PyTorch reimplementation for "PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors" https://arxiv.org/abs/1808.10322

FPConv: Learning Local Flattening for Point Convolution, CVPR 2020

Trescope is a comprehensive 3D machine learning development tool devoted to improve developing experience and speed in 3D field, which helps researchers and developers to label, debug, visualize various 3D data

PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling （CVPR 2020）

A general 3D object detection codebse.

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.

The pytorch implementation of flownet3d: https://github.com/xingyul/flownet3d

Light-weight camera LiDAR calibration package for ROS using OpenCV and PCL (PnP + LM optimization)

Polylidar3D - Fast polygon extraction from 3D Data

DBNet: A Large-Scale Dataset for Driving Behavior Learning, CVPR 2018

Paperlist of awesome 3D detection methods

An integrated SfM (Structure from Motion) and MVS (Multi-View Stereo) solution.

Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review

A list of resources about deep learning solutions on 3D shape processing