A resource repository for 3D machine learning

3D Reconstruction Software

open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.

A curated list of papers & resources linked to 3D reconstruction from images.

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

The open source mesh processing system

Open source Structure-from-Motion pipeline

Photogrammetric Computer Vision Framework

open Multi-View Stereo reconstruction library

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

Bundler Structure from Motion Toolkit

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

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

gradslam is an open source differentiable dense SLAM library for PyTorch

Index repo for Kimera code

End-to-end, automatic face swapping pipeline

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

A fast and robust point cloud registration library

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

An Invitation to 3D Vision: A Tutorial for Everyone

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

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

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

[Siggraph Asia 2013] Large-Scale, Real-Time 3D Reconstruction

Fuse multiple depth frames into a TSDF voxel volume.

A list of recent papers, libraries and datasets about 3D shape/geometry analysis (by topics, updating).

This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"

A list of papers and resources (data,code,etc) for holistic 3D reconstruction in computer vision