163 Open source projects that are alternatives of or similar to Factored3d

Matchable Image Retrieval by Learning from Surface Reconstruction

End-to-end, automatic face swapping pipeline

🔥PCL（Point Cloud Library）点云库学习记录

3D modeling from uncalibrated images

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

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

gradslam is an open source differentiable dense SLAM library for PyTorch

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

An Invitation to 3D Vision: A Tutorial for Everyone

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

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

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

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

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

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！

RGB-D Reconstruction Toolkit

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

A resource repository for 3D machine learning

An OpenCV-based structured light processing toolkit.

A fast and robust point cloud registration library

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

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

Photomodeling plugin for Maya

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

Implicit Geometric Regularization for Learning Shapes

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

PyTorch implementation of CloudWalk's recent work DenseBody

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

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

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

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/.

Dense 3D reconstruction from stereo (using LIBELAS)

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

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

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

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

Photogrammetric Computer Vision Framework

Index repo for Kimera code

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

3D Reconstruction Software

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

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

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

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

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

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

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

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

Training & Inference Code of PRNet in PyTorch 1.1.0

Fuse multiple depth frames into a TSDF voxel volume.

3D human face estimation and rendering from a single image

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

Set of images for doing 3d reconstruction

Bundler Structure from Motion Toolkit

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

FLaME: Fast Lightweight Mesh Estimation

SurfelWarp: Efficient Non-Volumetric Dynamic Reconstruction

open Multi-View Stereo reconstruction library

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