Top 164 3d-reconstruction open source projects

Code for 3D Reconstruction of Novel Object Shapes from Single Images paper

Demonstration of different algorithms and operations on faces. Join the Discord channel for discussion.

ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)

[WACV 2021] Dynamic Plane Convolutional Occupancy Networks

CVPR2021 paper "Learning Parallel Dense Correspondence from Spatio-Temporal Descriptorsfor Efficient and Robust 4D Reconstruction"

MVSNet: Depth Inference for Unstructured Multi-view Stereo using pytorch-lightning

Implementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

Official repository for the ShapeFormer Project

A python tool for fitting primitives 3D shapes in point clouds using RANSAC algorithm

Creating a 3D reconstruction of an object using multiple images

SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification - ECCV 2020 oral

Implementation for paper "Learning Single-View 3D Reconstruction with Limited Pose Supervision".

[ICCV21] Code for "RetrievalFuse: Neural 3D Scene Reconstruction with a Database"

Official repository for the paper "Learning Local Neighboring Structure for Robust 3D Shape Representation"

Collecting papers about new view synthesis

Semantic-TSDF for Self-driving Static Scene Reconstruction

🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)

Adaptive Surface Reconstruction for 3D Data Processing

An application displaying 2D/3D Dicom

a 3D-Reconstruction demo done with Kinect

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

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

Escaping Plato’s Cave: 3D Shape from Adversarial Rendering [ICCV 2019]

Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance (ECCV2020)

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

Visual Odometry with Inertial and Depth (VOID) dataset

[NeurIPS'21] Shape As Points: A Differentiable Poisson Solver

Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces

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

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

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

The 3D Public Transport Simulator is a Unity-based simulation, which uses OpenStreetMap data in order to support the simulation of worldwide locations. The development was part of a Bachelor thesis.

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

A Collection of Algorithms for Relative Pose Estimation of a Calibrated Camera

A readable implementation of structure-from-motion

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

The detection of peaks and valleys in a 1d-vector or 2d-array (image)

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

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.

Global L0 algorithm for regularity-constrained plane fitting

Graduation Project: A point cloud semantic segmentation and VIO based 3D reconstruction method using RGB-D and IMU

API to support AIST++ Dataset: https://google.github.io/aistplusplus_dataset

Motion Averaging

This demo uses a deep neural network and two generic cameras to perform 3D pose estimation.