lyfadvance/Awesome-MVS

Awesome list of multi-view stereo papers

Awesome-MVS

Contributions welcomed!

Learning-based MVS Methods

2023

MosaicMVS: Mosaic-based Omnidirectional Multi-view Stereo for Indoor Scenes

• 
• 
• 

DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo

• 
• 

360MVSNet: Deep Multi-view Stereo Network with 360◦ Images for Indoor Scene Reconstruction

• 
• 
• 

nLMVS-Net: Deep Non-Lambertian Multi-View Stereo

• 
• 
• 

Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity

• 
• 

MVSFormer: Multi-View Stereo with Pre-trained Vision Transformers and Temperature-based Depth

• 
• 
• 

2022

Multistage Pixel-Visibility Learning With Cost Regularization for Multiview Stereo

• 
• 

Global Contextual Complementary Network for Multi-View Stereo

• 
• 
• 

Hybrid Cost Volume Regularization for Memory-efficient Multi-view Stereo Networks - [HR-MVSNet]

• 
• 
• 

Sparse Prior Guided Deep Multi-view Stereo - [SPGNet]

• 
• 

Uncertainty-guided Multi-view Stereo Network for Depth Estimation - [UGNet]

• 
• 

Adaptive Range guided Multi-view Depth Estimation with Normal Ranking Loss - [BDE-MVSNet]

• 
• 

ElasticMVS: Learning Elastic Part Representation for Self-Supervised Multi-view Stereopsis

• 
• 

WT-MVSNet: Window-based Transformers for Multi-view Stereo

• 
• 

Multi-View Guided Multi-View Stereo - [Guided-MVS]

• 
• 
• 

ParseMVS: Learning Primitive-aware Surface Representations for Sparse Multi-view Stereopsis

• 
• 

Self-Supervised Multi-view Stereo via Adjacent Geometry Guided Volume Completion

• 
• 
• 

Self-supervised Multi-view Stereo via Inter and Intra Network Pseudo Depth

• 
• 
• 

Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling

• 
• 

PSP-MVSNet: Deep Patch-Based Similarity Perceptual for Multi-view Stereo Depth Inference

• 
• 

End-to-End Multi-View Structure-from-Motion with Hypercorrelation Volumes

• 
• 

A Benchmark and a Baseline for Robust Multi-view Depth Estimation

• 
• 
• 

Cost Volume Pyramid Network with Multi-strategies Range Searching for Multi-view Stereo - [MSCVP-MVSNet]

• 
• 
• 

ATLAS-MVSNet: Attention Layers for Feature Extraction and Cost Volume Regularization in Multi-View Stereo

• 
• 
• 
• 

DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis

• 
• 
• 
• 

IS-MVSNet: Importance-sampling-based MVSNet

• 
• 
• 

KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo

• 
• 
• 
• 

Semi-supervised Deep Multi-view Stereo

• 
• 

Miper-MVS: Multi-Scale Itearative Probability Estimation with Refinement for Efficient Multi-View Stereo

• 
• 
• 

RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering

• 
• 
• 
• 

Enhancing Multi-view Stereo with Contrastive Matching and Weighted Focal Loss

• 
• 

MVSTER: Epipolar Transformer for Efficient Multi-View Stereo

• 
• 
• 

Multiview Stereo with Cascaded Epipolar RAFT - [CER-MVS]

• 
• 
• 

Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction

• 
• 

RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo

• 
• 

Bidirectional Hybrid LSTM Based Recurrent Neural Network for Multi-view Stereo - [BH-MVSNet]

• 
• 

Exploiting Correspondences with All-pairs Correlations for Multi-view Depth Estimation

• 
• 

Multi-View Stereo with Transformer - [MVSTR]

• 
• 

MVS-T: A Coarse-to-Fine Multi-View Stereo Network with Transformer for Low-Resolution Images 3D Reconstruction

• 
• 

Efficient Multi-View Stereo by Iterative Dynamic Cost Volume

• 
• 
• 

Non-parametric Depth Distribution Modelling based Depth Inference for Multi-view Stereo - [NP-CVP-MVS]

• 
• 
• 

Generalized Binary Search Network for Highly-Efficient Multi-View Stereo - [GBi-Net]

• 
• 
• 

Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation and Focal Loss - [UniMVSNet]

• 
• 
• 
• 

TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers

• 
• 
• 
• 

IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo

• 
• 
• 

Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry - [MaGNet]

• 
• 
• 

Curvature-guided dynamic scale networks for Multi-view Stereo - [CDS-MVSNet]

• 
• 
• 
• 

DDL-MVS: Depth Discontinuity Learning for MVS Networks - [iMVS]

• 
• 
• 

PatchMVSNet: Patch-wise Unsupervised Multi-View Stereo for Weakly-Textured Surface Reconstruction

• 
• 

PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo

• 
• 

RayMVSNet: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo

• 
• 
• 

DRI-MVSNet: A depth residual inference network for multi-view stereo images

• 
• 

A Semi‑Supervised Method for PatchMatch Multi‑View Stereo with Sparse Points

• 
• 

DEMVSNet: Denoising and Depth Inference for Unstructured Multi‐view Stereo on Noised Images

• 
• 

Learning Inverse Depth Regression for Pixelwise Visibility-Aware Multi-View Stereo Networks - [PVSNet]

• 
• 

2021

Long-range Attention Network for Multi-View Stereo

• 
• 
• 

PatchmatchNet: Learned Multi-View Patchmatch Stereo

• 
• 
• 

DeepVideoMVS: Multi-View Stereo on Video With Recurrent Spatio-Temporal Fusion

• 
• 
• 
• 

Self-Supervised Learning of Depth Inference for Multi-View Stereo

• 
• 
• 
• 

Mˆ3VSNet: Unsupervised multi-metric multi-view stereo network

• 
• 
• 
• 

AA-RMVSNet: Adaptive Aggregation Recurrent Multi-View Stereo Network

• 
• 
• 

Digging into Uncertainty in Self-supervised Multi-view Stereo

• 
• 
• 
• 

Self-supervised multi-view stereo via effective co-segmentation and data-augmentation

• 
• 
• 
• 

MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions

• 
• 
• 
• 

IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions

• 
• 
• 

EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo

• 
• 
• 
• 

NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-View Stereo

• 
• 
• 
• 

Just a Few Points Are All You Need for Multi-View Stereo: A Novel Semi-Supervised Learning Method for Multi-View Stereo

• 
• 

Learning Signed Distance Field for Multi-view Surface Reconstruction - [MVSDF]

• 
• 
• 

PatchMatch-RL: Deep MVS With Pixelwise Depth, Normal, and Visibility

• 
• 
• 

Deep Multi-View Stereo Gone Wild

• 
• 
• 
• 

HighRes-MVSNet: A Fast Multi-View Stereo Network for Dense 3D Reconstruction From High-Resolution Images

• 
• 

AACVP-MVSNet: Attention-aware cost volume pyramid based multi-view stereo network for 3D reconstruction. ISPRS Journal of Photogrammetry and Remote Sensing

• 
• 
• 

Non-local Recurrent Regularization Networks for Multi-view Stereo

• 
• 

DDR-Net: Learning Multi-Stage Multi-View Stereo With Dynamic Depth Range

• 
• 
• 

TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo - [CVA-MVSNet]

• 
• 
• 
• 

2020

BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo Networks

• 
• 
• 
• 

MVSNet++: Learning Depth-Based Attention Pyramid Features for Multi-View Stereo

• 
• 
• 

Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching

• 
• 
• 
• 

BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo

• 
• 

Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness - [UCSNet]

• 
• 
• 
• 

Fast-MVSNet: Sparse-to-Dense Multi-View Stereo with Learned Propagation and Gauss-Newton Refinement

• 
• 
• 
• 

Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume - [CIDER]

• 
• 
• 

Attention-Aware Multi-View Stereo - [AttMVSNet]

• 
• 

A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset

• 
• 
• 
• 

Cost Volume Pyramid Based Depth Inference for Multi-View Stereo - [CVP-MVSNet]

• 
• 
• 

Pyramid Multi-view Stereo Net with Self-adaptive View aggregation - [PVAMVSNet]

• 
• 
• 

Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking

• 
• 
• 

Learning to Adapt Multi-View Stereo by Self-Supervision

• 
• 
• 

Visibility-aware Multi-view Stereo Network - [Vis-MVSNet]

• 
• 
• 

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

• 
• 
• 
• 

NRMVS: Non-Rigid Multi-View Stereo

• 
• 

2019

Multi-view Stereo by Temporal Nonparametric Fusion

• 
• 
• 
• 

DPSNet: End-to-end Deep Plane Sweep Stereo

• 
• 
• 

Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference - [RMVSNet]

• 
• 
• 

Point-Based Multi-View Stereo Network - [PointMVSNet]

• 
• 
• 
• 

P-MVSNet: Learning Patch-wise Matching Confidence Aggregation for Multi-view Stereo

• 
• 

MVSCRF: Learning Multi-view Stereo with Conditional Random Fields

• 
• 

Learning unsupervised multi-view stereopsis via robust photometric consistency

• 
• 
• 
• 

MVS2: Deep Unsupervised Multi-View Stereo with Multi-View Symmetry

• 
• 
• 

2018

DeepMVS: Learning Multi-view Stereopsis

• 
• 
• 
• 

MVDepthNet: Real-time Multiview Depth Estimation Neural Network

• 
• 
• 

MVSNet: Depth Inference for Unstructured Multi-view Stereo

• 
• 
• 
• 

2017

SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis

• 
• 
• 

PatchMatch-based MVS Methods

2022

LGP-MVS: Combined Local and Global Planar Priors Guidance for Indoor Multi-View Stereo

• 
• 

Multi-View Depth Estimation with Color-Aware Propagation and Texture-Aware Triangulation

• 
• 

Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo - [ACMMP]

• 
• 

Revisiting PatchMatch Multi-View Stereo for Urban 3D Reconstruction

• 

2021

PHI-MVS: Plane Hypothesis Inference Multi-view Stereo for Large-Scale Scene Reconstruction

• 
• 
• 

DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes

• 
• 
• 

Adaptive Pixelwise Inference Multi-View Stereo

• 
• 

2020

Mesh-Guided Multi-View Stereo with Pyramid Architecture - [MG-MVS]

• 
• 

Planar Prior Assisted PatchMatch Multi-View Stereo - [ACMP]

• 
• 
• 

DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction

• 
• 

MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction

• 
• 
• 

Confidence-based Large-scale Dense Multi-view Stereo - [CLD-MVS]

• 
• 

A-TVSNet: Aggregated Two-View Stereo Network for Multi-View Stereo Depth Estimation

• 
• 
• 

2019

Multi-Scale Geometric Consistency Guided Multi-View Stereo - [ACMH, ACMM]

• 
• 
• 

TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo

• 
• 

Plane Completion and Filtering for Multi-View Stereo Reconstruction - [PCFMVS]

• 
• 

Pyramid Multi-View Stereo with Local Consistency - [PLC]

• 
• 

early

Accurate, Dense, and Robust Multi-View Stereopsis - [Furu / PMVS]

• 
• 

Efficient large-scale multi-view stereo for ultra high-resolution image sets - [Tola / EMVS]

• 
• 

Using multiple hypotheses to improve depth-maps for multi-view stereo - [Camp]

• 

Patchmatch stereo-stereo matching with slanted support windows

• 
• 

Pixelwise view selection for unstructured multi-view stereo - [COLMAP]

• 
• 

Massively Parallel Multiview Stereopsis by Surface Normal Diffusion - [Gipuma]

• 
• 
• 

A TV prior for high-quality scalable multi-view stereo reconstruction

• 

---

Other Resources

• awesome-mvs
• Awesome-Learning-MVS