73 Open Source 3D Vision Software Projects
Free and open source 3d vision code projects including engines, APIs, generators, and tools.
3D Pose Baseline 1177 ⭐
A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.
Minkowskiengine 1470 ⭐
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
Boofcv 811 ⭐
Fast computer vision library for SFM, calibration, fiducials, tracking, image processing, and more.
Depth Vo Feat 314 ⭐
Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction
Monoloco 326 ⭐
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.
Monoport 406 ⭐
Volumetric Human Teleportation (SIGGRAPH 2020 Real-Time Live) Monocular Real-Time Volumetric Performance Capture(ECCV 2020)
Deeperinversecompositionalalgorithm 142 ⭐
Taking a Deeper Look at the Inverse Compositional Algorithm (CVPR 2019, Oral)
Learningrigidity 134 ⭐
Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation (ECCV 2018)
Tailornet 263 ⭐
Code for our CVPR 2020 (ORAL) paper - TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style.
Spatiotemporalsegmentation 186 ⭐
4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)
Unsupervised Depth Completion Visual Inertial Odometry 141 ⭐
Tensorflow implementation of Unsupervised Depth Completion from Visual Inertial Odometry (in RA-L January 2020 & ICRA 2020)
Ciwt 83 ⭐
This repository contains code for the tracking system as described in ''Combined Image- and World-Space Tracking in Traffic Scenes'', ICRA 2017.
Disn 102 ⭐
(latest updates and bug fixed) DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction
Layered Scene Inference 78 ⭐
Code accompanying the paper "Layer-structured 3D Scene Inference via View Synthesis", ECCV 2018
Generative_pose 58 ⭐
Code for our ICCV 19 paper : Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking
Refresh 48 ⭐
Create RefRESH data: dataset tools for Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation (ECCV 2018)
Awesome State Of Depth Completion 136 ⭐
Current state of supervised and unsupervised depth completion methods
Contactdb_prediction 24 ⭐
Code for CVPR 2019 paper "ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging"
Adareg Monodispnet 22 ⭐
Repository for Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction (CVPR2019)
Paiconvmesh 18 ⭐
Official repository for the paper "Learning Local Neighboring Structure for Robust 3D Shape Representation"
Associative3D 24 ⭐
Code release for our ECCV 2020 paper "Associative3D: Volumetric Reconstruction from Sparse Views"
Fclib 42 ⭐
OnePiece (libonepiece) is a RGB-D based 3D vision library, you can easily use OPLib to build a SLAM system and extract a 3D model.
Finding Your Center 16 ⭐
Public repository for paper "Finding Your (3D) Center: 3D object detection using a learned loss"
Google Research Datasets Objectron 1619 ⭐
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
Neuralrecon 797 ⭐
Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
Unsupervisedrr 97 ⭐
[CVPR 2021 - Oral] UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering
Rel3D 24 ⭐
Official code for NeurRIPS 2020 paper "Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D"
Scannet Layout 23 ⭐
We introduce the ScanNet-Layout dataset for benchmarking general 3D room layout estimation from single view.
Randla Net Pytorch 35 ⭐
:four_leaf_clover: Pytorch Implementation of RandLA-Net (https://arxiv.org/abs/1911.11236)
Lowshot Shapebias 35 ⭐
Learning low-shot object classification with explicit shape bias learned from point clouds
Vincentfung13 Mine 196 ⭐
Code and models for our ICCV 2021 paper "MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis"
Snarf 142 ⭐
Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.
Object_nerf 112 ⭐
Code for "Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering", ICCV 2021
Lemo 124 ⭐
Official Pytorch implementation for 2021 ICCV paper "Learning Motion Priors for 4D Human Body Capture in 3D Scenes" and trained models / data
Simpleview 87 ⭐
Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"
Egonet 87 ⭐
Official project website for the CVPR 2021 paper "Exploring intermediate representation for monocular vehicle pose estimation"
Curvenet 87 ⭐
Official implementation of "Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis", ICCV 2021
Learning Topology Synthetic Data 22 ⭐
Tensorflow implementation of Learning Topology from Synthetic Data for Unsupervised Depth Completion (RAL 2021 & ICRA 2021)
Calibrated Backprojection Network 41 ⭐
PyTorch Implementation of Unsupervised Depth Completion with Calibrated Backprojection Layers (ORAL, ICCV 2021)
Simpleview Pytorch 10 ⭐
PyTorch implementation of SimpleView from "Revisiting Point Cloud Classification with a Simple and Effective Baseline", Goyal et al. (2020)
Redal 11 ⭐
🍀 Official pytorch implementation of "ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation. Wu et al. ICCV 2021."