All Projects → XYZ-qiyh → Awesome Learning Mvs

XYZ-qiyh / Awesome Learning Mvs

A list of awesome learning-based multi-view stereo papers

Projects that are alternatives of or similar to Awesome Learning Mvs

Blender Addon Photogrammetry Importer
Addon to import different photogrammetry formats into Blender
Stars: ✭ 292 (+981.48%)
Mutual labels:  sfm, structure-from-motion
Dagsfm
Distributed and Graph-based Structure from Motion
Stars: ✭ 269 (+896.3%)
Mutual labels:  sfm, structure-from-motion
Uav Mapper
UAV-Mapper is a lightweight UAV Image Processing System, Visual SFM reconstruction or Aerial Triangulation, Fast Ortho-Mosaic, Plannar Mosaic, Fast Digital Surface Map (DSM) and 3d reconstruction for UAVs.
Stars: ✭ 106 (+292.59%)
Mutual labels:  sfm, structure-from-motion
Openmvg
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
Stars: ✭ 3,902 (+14351.85%)
Mutual labels:  sfm, structure-from-motion
kapture-localization
Provide mapping and localization pipelines based on kapture format
Stars: ✭ 111 (+311.11%)
Mutual labels:  structure-from-motion, sfm
Kapture
kapture is a file format as well as a set of tools for manipulating datasets, and in particular Visual Localization and Structure from Motion data.
Stars: ✭ 128 (+374.07%)
Mutual labels:  sfm, structure-from-motion
how-to-sfm
A self-reliant tutorial on Structure-from-Motion
Stars: ✭ 112 (+314.81%)
Mutual labels:  structure-from-motion, sfm
DenseDescriptorLearning-Pytorch
Official Repo for the paper "Extremely Dense Point Correspondences using a Learned Feature Descriptor" (CVPR 2020)
Stars: ✭ 66 (+144.44%)
Mutual labels:  structure-from-motion, sfm
Mvstudio
An integrated SfM (Structure from Motion) and MVS (Multi-View Stereo) solution.
Stars: ✭ 154 (+470.37%)
Mutual labels:  sfm, structure-from-motion
Monocularsfm
Monocular Structure from Motion
Stars: ✭ 128 (+374.07%)
Mutual labels:  sfm, structure-from-motion
simple-sfm
A readable implementation of structure-from-motion
Stars: ✭ 19 (-29.63%)
Mutual labels:  structure-from-motion, sfm
cv-arxiv-daily
🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)
Stars: ✭ 216 (+700%)
Mutual labels:  structure-from-motion, sfm
Rotation Coordinate Descent
(CVPR 2020 Oral) A fast global rotation averaging algorithm.
Stars: ✭ 44 (+62.96%)
Mutual labels:  sfm
Deep-SfM-Revisited
No description or website provided.
Stars: ✭ 124 (+359.26%)
Mutual labels:  structure-from-motion
Boofcv
Fast computer vision library for SFM, calibration, fiducials, tracking, image processing, and more.
Stars: ✭ 706 (+2514.81%)
Mutual labels:  structure-from-motion
pybot
Research tools for autonomous systems in Python
Stars: ✭ 60 (+122.22%)
Mutual labels:  structure-from-motion
sfm
simple file manager
Stars: ✭ 163 (+503.7%)
Mutual labels:  sfm
Gms Feature Matcher
GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence (CVPR 17 & IJCV 20)
Stars: ✭ 797 (+2851.85%)
Mutual labels:  sfm
Theiasfm
An open source library for multiview geometry and structure from motion
Stars: ✭ 647 (+2296.3%)
Mutual labels:  structure-from-motion
Odm
A command line toolkit to generate maps, point clouds, 3D models and DEMs from drone, balloon or kite images. 📷
Stars: ✭ 3,340 (+12270.37%)
Mutual labels:  structure-from-motion

Awesome-Learning-MVS (Methods and Datasets)

Content of this repo

  1. Learning based MVS
  2. Learning based Multi-view depth estimation
  3. Unsupervised Learning MVS

Learning-based MVS Methods

  1. Volumetric methods (SurfaceNet)
  2. Depthmap based methods (MVSNet/R-MVSNet and so on)

ICCV2017

  • SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis [paper] [Github] [T-PAMI]

ECCV2018

  • MVSNet: Depth Inference for Unstructured Multi-view Stereo [paper] [Github]

CVPR2019

  • Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference [paper] [supp] [Github]

ICCV2019

  • Point-Based Multi-View Stereo Network [paper] [supp] [Github] [T-PAMI]
  • P-MVSNet: Learning Patch-wise Matching Confidence Aggregation for Multi-view Stereo [paper]
  • MVSCRF: Learning Multi-view Stereo with Conditional Random Fields [paper]

AAAI2020

  • Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume [paper] [Github]

CVPR2020

  • Cascade Cost Volume for High-Resolutoin Multi-View Stereo and Stereo Matching [paper] [Github]

  • Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness [paper] [supp] [Github]

  • Cost Volume Pyramid Based Depth Inference for Multi-View Stereo [paper] [supp] [Github]

  • Fast-MVSNet: Sparse-to-Dense Multi-View Stereo with Learned Propagation and Gauss-Newton Refinement [paper] [supp] [Github]

  • Attention-Aware Multi-View Stereo [paper]

  • A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset [paper] [Github] [data]

ECCV2020

  • Pyramid Multi-view Stereo Net with Self-adaptive View aggregation [paper] [Github]
  • Dense Hybird Recurrent Multi-view Stereo Net with Dynamic Consistency Checking [paper] [Github]

BMVC2020

  • Visibility-aware Multi-view Stereo Network [paper] [Github]

WACV2021

  • Long-range Attention Network for Multi-View Stereo [paper]

CVPR2021

  • PatchmatchNet: Learned Multi-View Patchmatch Stereo [paper] [Github]

ArXiv Paper

  • PVSNet: Pixelwise Visibility-Aware Multi-View Stereo Network [paper]

Survey Paper

  • A Survey on Deep Learning Techniques for Stereo-based Depth Estimation [paper]

To Be Continued...

Multi-view Stereo Benchmark

  • DTU [CVPR2014, IJCV2016]

  • Tanks and Temples [ACM ToG2017]

  • ETH3D [CVPR2017]

    • A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos [paper] [supp] [website] [Github]
  • BlendedMVS [CVPR2020]

    • BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo Network [paper] [supp] [Github] [visual]

Large-scale Real-world Scenes

  1. Chinese Style Architectures
  1. Western Style Architectures
  1. Aerial Dataset

Welcome to contribute to this Repo!

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].