368 Open source projects that are alternatives of or similar to Pcn

Adaptive Surface Reconstruction for 3D Data Processing

End-to-end, automatic face swapping pipeline

Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021 Oral)

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

a 3D-Reconstruction demo done with Kinect

🚕 Fast and robust clustering of point clouds generated with a Velodyne sensor.

Making Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures

🔥3D-RecGAN in Tensorflow (ICCV Workshops 2017)

This repository contains the source codes for the paper "DmifNet: 3D Shape Reconstruction based on Dynamic Multi–Branch Information Fusion (ICPR 2020 Oral)"

Matterport3D is a pretty awesome dataset for RGB-D machine learning tasks :)

C++ code for triangulating Point Cloud data and displaying it

Robotics with GPU computing

An Invitation to 3D Vision: A Tutorial for Everyone

Deep Single-View 3D Object Reconstruction with Visual Hull Embedding

FPConv: Learning Local Flattening for Point Convolution, CVPR 2020

Roof Classification, Segmentation, and Damage Completion using 3D Point Clouds

Algorithm to texture 3D reconstructions from multi-view stereo images

Code release for "Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene"

Superpixel-based semantic segmentation, with object pose estimation and tracking. Provided as a ROS package.

Implementations of a rather simple version of the Iterative Closest Point algorithm in various languages.

LiveScan3D is a system designed for real time 3D reconstruction using multiple Azure Kinect or Kinect v2 depth sensors simultaneously at real time speed.

[cvpr19] Hands+Objects synthetic dataset, instructions to download and code to load the dataset

Code release for "Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction"

30th June, 2019 - 30th June, 2020. Robotics and Machine Intelligence Lab, The Hong Kong Polytechnic University. This work is supported in part by the Chinese National Engineering Research Centre for Steel Construction (Hong Kong Branch) at The Hong Kong Polytechnic University under grant BBV8, in part by the Research Grants Council of Hong Kong …

Python code to fuse multiple RGB-D images into a TSDF voxel volume.

[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

Implementation of the Point Transformer layer, in Pytorch

Multi-view 3D reconstruction using neural rendering. Unofficial implementation of UNISURF, VolSDF, NeuS and more.

blender python scripts

our code for paper 'PointCutMix: Regularization Strategy for Point Cloud Classification'

real-time 3D reconstruction of non-rigidly deforming scenes using depth data

A ground segmentation algorithm for 3D point clouds based on the work described in “Fast segmentation of 3D point clouds: a paradigm on LIDAR data for Autonomous Vehicle Applications”, D. Zermas, I. Izzat and N. Papanikolopoulos, 2017. Distinguish between road and non-road points. Road surface extraction. Plane fit ground filter

Draco is a library for compressing and decompressing 3D geometric meshes and point clouds. It is intended to improve the storage and transmission of 3D graphics.

register 3D point clouds using rotation, translation, and scale transformations.

Implementation of ICCV19 Paper "Learning Two-View Correspondences and Geometry Using Order-Aware Network"

Automatically registers (aligns) and visualizes point clouds, or processes a whole bunch at once

Paper reading notes on Deep Learning and Machine Learning

No description or website provided.

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

MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition

A lightweight, easy-to-use, and efficient C++ library for processing and rendering 3D data

A readable implementation of structure-from-motion

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

[CVPR 2021] Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis (official pytorch implementation)

PyTorch implementation of CloudWalk's recent work DenseBody

[3DV 2021] DSP-SLAM: Object Oriented SLAM with Deep Shape Priors

Tensorflow implementation of Unsupervised Depth Completion from Visual Inertial Odometry (in RA-L January 2020 & ICRA 2020)

A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package

Real-Time 3D Semantic Reconstruction from 2D data

This project is to convert PortraitFCN+ (by Xiaoyong Shen) from Matlab to Tensorflow, then refine the outputs from it (converted to a trimap) using KNN and ResNet, supervised by Richard Berwick.

Paperlist of awesome 3D detection methods

SGM，立体匹配最经典应用最广泛算法，4000+引用，兼顾效率和效果。完整实现，代码规范，注释清晰，博客教学，欢迎star！

Code for Learnt Stereo Machines based on the NIPS 2017 paper

Associatively Segmenting Instances and Semantics in Point Clouds, CVPR 2019

Differentiable Point Cloud Sampling (CVPR 2020 Oral)

Code for our CVPR 2020 (ORAL) paper - TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style.

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

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

Learning Video Representations from Correspondence Proposals (CVPR 2019 Oral)