Top 164 3d-reconstruction open source projects

List of projects for 3d reconstruction

Code and Data Release for GenRe (NeurIPS 2018) and ShapeHD (ECCV 2018)

A list of papers and datasets about point cloud analysis (processing)

Code for PCN: Point Completion Network in 3DV'18 (Oral)

Code for Learnt Stereo Machines based on the NIPS 2017 paper

[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

PatchMatch，倾斜窗口经典，效果极佳，OpenMVS&Colmap稠密匹配算法。完整实现，代码规范，注释清晰，博客教学，欢迎star！

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

[CVPR'18] ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans

3D reconstruction, sfm with Python3

Pytorch implementation of HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation.

Tensorflow framework for the FLAME 3D head model. The code demonstrates how to sample 3D heads from the model, fit the model to 2D or 3D keypoints, and how to generate textured head meshes from Images.

Morphing and Sampling Network for Dense Point Cloud Completion (AAAI2020)

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

Code for GAN2Shape (ICLR2021 oral)

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

The open source mesh processing system

Open source Structure-from-Motion pipeline

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

A differentiable 3D renderer with Pytorch, Tensorflow and Matlab interfaces

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

FLaME: Fast Lightweight Mesh Estimation

This is a implementation of the 3D FLAME model in PyTorch

An OpenCV-based structured light processing toolkit.

Training & Inference Code of PRNet in PyTorch 1.1.0

SurfelWarp: Efficient Non-Volumetric Dynamic Reconstruction

Code release for "Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency" (CVPR 2017)

AD-Census立体匹配算法，中国学者Xing Mei等人研究成果（Respect！），算法效率高、效果出色，适合硬件加速，Intel RealSense D400 Stereo模块算法。完整实现，代码规范，注释清晰，欢迎star！

Photogrammetric Computer Vision Framework

[CVPR 2017] Generation and reconstruction of 3D shapes via modeling multi-view depth maps or silhouettes

[cvpr19] Demo, training and evaluation code for generating dense hand+object reconstructions from single rgb images

Photomodeling plugin for Maya

Set of images for doing 3d reconstruction

open Multi-View Stereo reconstruction library

[CVPR'17] Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis

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

Dense 3D reconstruction from stereo (using LIBELAS)

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

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

[CVPR'20] SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans

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

🔥PCL（Point Cloud Library）点云库学习记录

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

[ECCV'18 Oral] PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes

🔥3D-RecGAN++ in Tensorflow (TPAMI 2018)

3D human face estimation and rendering from a single image

Implicit Geometric Regularization for Learning Shapes

Bundler Structure from Motion Toolkit

As a part of HAKE project (HAKE-3D). Code for our CVPR2020 paper "Detailed 2D-3D Joint Representation for Human-Object Interaction".

Python Wrapper for MeshFix: easily repair holes in PyVista surface meshes

3D reconstruction with neural networks using Tensorflow. See link for Video (https://www.youtube.com/watch?v=iI6ZMST8Ri0)

A collaborative list of awesome CryoEM (Cryo Electron Microscopy) resources.

3D modeling from uncalibrated images

A set of MATLAB utilities for multiple view geometry, provided alongside Hartley & Zisserman's "Multiple View Geometry in Computer Vision, Second Edition" (2004). Obtained from http://www.robots.ox.ac.uk/~vgg/hzbook/code/.

Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path, ICCV 2019

This repository contains the code for the paper "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization"

Matchable Image Retrieval by Learning from Surface Reconstruction

[Siggraph 2017] BundleFusion: Real-time Globally Consistent 3D Reconstruction using Online Surface Re-integration