【立体匹配---文献整理】(总)
目录
001综述
002传统算法
002.01 局部方法
002.02 全局方法
002.03 efficent方法
002.04 不分类了
003机器学习
003.01 其他
003.02 深度学习
004数据集
001 综述
(1)cooperative computation of stereo disparity
1976
(2)a taxonomy and evaluation of dense two-frame stereo correspondence algorithms
2001
(3)literature survey on stereo vision disparity map algorithms
2016
(4)Review of stereo vision algorithms and their suitability for resource-limited systems 2013
(5)双目立体匹配算法的研究与进展
(6)双目视觉的立体匹配算法研究进展
(7)基于深度学习的双目立体匹配方法综述
001.02 置信度
(1)A Quantitative Evaluation of Confidence Measures for Stereo Vision
// 2012
(2)On the confidence of stereo matching in a deep-learning era: a quantitative evaluation
// 2021
002 传统
● 002.01局部方法
(1)locally adaptive support-weight approach for visual correspondence search
2005
(2)fast cost-volume filtering for visual correspondence and beyond
2011
(3)simple but effective tree structures for dynamic programming-based stereo matching
(4)stereo processing by semiglobal matching and mutual information
2008 半全局匹配
● 002.02全局方法
(1)efficient belief propagation for early vision
2004
(2)segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure
2006
(3)computing visual correspondence with occlusions using graph cuts
2001 图割
● 002.03 efficient 算法
● (避免搜寻全部的视差范围)
(1)sped-up patchmatch belief propagation for continuous rmfs
2015 超像素
(2)patchmatchfilter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation
2013
(3)patchmatch stereo: stereo matching with slanted support windows
2011
(4)pmbp: patchmatch belief propagation for correspondence field estimation.
2021
(5)(patchmatch):a randomized correspondence algorithm for structural image editing
2009
(6)
002.04 算了,不分类了
(1)stereo processing by semiglobal matching and mutual information
2008 (TPAMI) SGM 半全局匹配
(2)Cross-Based Local Stereo Matching Using Orthogonal Integral Images
2009
(3)Cross-Scale Cost Aggregation for Stereo Matching
2014
(4)Improvement of stereo matching algorithm for 3D surface reconstruction
2018 梯度匹配+带有迭代引导滤波器(ASW iGF)的自适应支持权重(ASW)
(5)A hierarchical stereo matching algorithm based on adaptive support region aggregation method
2018 Census变体 (结合边缘信息)
(6)Stereo Matching Algorithm Based on Joint Matching Cost and Adaptive Window
2018 代价:SAD+Census 聚合:an adaptive window based on pilot filter
(7)A local stereo matching algorithm based on weighted guided image filtering for improving the generation of depth range images 2017
(8)High accuracy local stereo matching using DoG scale map 2017
(9)Calculating dense disparity maps from color stereo images, an efficient implementation 2001
(10)Non-parametric local transforms for computing visual correspondence 2005
(11)Stereo matching algorithm based on the combination of matching costs 2017
(12)基于树形结构的半全局立体匹配算法
(13)Real-time stereo vision system using semi-global matching disparity estimation: Architecture and (14)FPGA-implementatio 2010
(15)Iterative semi-global matching for robust driver assistance systems 2012
(16)R3SGM: Real-Time Raster-Respecting Semi-Global Matching for Power-Constrained Systems 2018
(17)High throughput hardware architecture for accurate semi-global matching
(18)Embedded Real-time Stereo Estimation via Semi-global Matching on the GPU 2016
(19)On building an accurate stereo matching system on graphics hardware
(21)A census-based stereo vision algorithm using modified Semi-Global Matching and plane fitting to improve matching quality
(22)基于改进Census变换的抗噪立体匹配算法
(23)Multi-frame stereo matching with edges, planes, and superpixels
(24)Efficient large-scale stereo matching 2010
(25)DSR: Direct Self-Rectification for Uncalibrated Dual-Lens Cameras
(26)A flexible new technique for camera calibration 2002 张正友标定 经典中的经典
003 机器学习
● 003.01 其他
● (随机森林、决策树等)
(1)learning to be a depth camera for close-range human capture and interaction
2014
(2)hyperdepth: learning depth from struectured light without matching
2016
(3)low compute and fully parallel computer vision
(4)ultrastereo: efficient learning based matching for active stereo systerms
(5)Continuous 3D Label Stereo Matching Using Local Expansion Moves
2018 马尔科夫随机场
● 003.02深度学习
(1)efficient deep learning for stereo matching
// 2016 内乘 多级分类
(2)computing the stereo matching cost with a convolutional neural network
// (MCNN)领域开篇山之作 2014 (cvpr)
(3)stereo matching by training a convolutional neural network to compare image patches.
// (依旧MC-CNN) 2016 (期刊JMLR)
(4)a large dataset to train convolutional networks fir disparity. optical flow, and scene flow estimation
// 2015 (cvpr) [sceneflow数据集 FlowNet ]
(5)improved stereo matchinh with constant highway networks and reflective confidence learning
// 2016 (cvpr) 没看过
(6)optical flow estimation using a spatial pyramid network
// 2016(cvpr)光流估计的文章 乱入
(7)AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
// 2020 (arxiv) 对input/cost volume/output的域对齐
(8)GCNet :End-to-End Learning of Geometry and Context for Deep Stereo Regression
// 2017 (ICCV) GCNet (开篇之作)经典 推荐
(9)FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
// 2017 (CVPR) FlowNet 2.0 (本文是FlowNet的进化版,由于FlowNet是基于CNN光流估计的开创之作)
(10)CRL:Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
// 2017 (ICCVW) CRL
(11)PSMNet:Pyramid stereo matching network.
// 2018 (CVPR) PSMNet 典中典 必读 承接GCNet
(12)iResNet:Learning for disparity estimation through feature constancy
// 2018 (CVPR) iResNet
(13)Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling
// 2017 (CVPR) 标签优化通用框架
(14)HSM: Hierarchical Deep Stereo Matching on High-Resolution Images
// 2019 (CVPR) 高分辨率 非对称增强
(15)GA-Net: Guided Aggregation Net for End-to-end Stereo Matching
// 2019 (CVPR) 经典
(16)StereoNet: Guided Hierarchical Refinement for Edge-Aware Depth Prediction
// 2018 (ECCV) 经典轻量 (号称60fps)
(17)ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems
// 2018 (ECCV)轻量+主动式 经典
(18)HashMatch: Low compute and fully parallel computer vision with hashmatch
// 2017 (ICCV) CRF +CNN
(19)UltraStereo: Efficient Learning-Based Matching for Active Stereo Systems
// 2017 (CVPR)无监督贪婪优化 500Hz
(20)SOS: Stereo Matching in O(1) with Slanted Support Windows
// 2018 (IROS) GPU架构上以4000帧/秒的速度运行
(21)StereoDRNet: Dilated Residual Stereo Net
// 2019 (CVPR) 多尺度3D空洞卷积(ASPP) Vortex Pooling 进行特征提取
(22)LEAStereo: Hierarchical Neural Architecture Search for Deep Stereo Matching
// 2020 (NIPS) NAS搜索
(23)Deeppruner: Learning efficient stereo matching via differentiable patchmatch
// 2019 (ICCV) 轻量经典
(24)DSMNet : Domain-invariant Stereo Matching Networks
// 2019 (ECCV) 域不变(Domain-Invariant) 结构保存滤波器(SGF)
(25)AANet: Adaptive Aggregation Network for Efficient Stereo Matching
// 2020 (CVPR) 轻量 经典 (形变卷积)
(26)EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection
// 2018 (ACCV) 训练一个边缘子网络预测边缘图
(27)Guided Stereo Matching
// 2019 利用了少量从外部源检索到的稀疏但可靠的深度测量值
(28)Efficient Multi-Scale Stereo-Matching Network Using Adaptive Cost Volume Filtering
// 2022(Sensors)
(29)SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selection
// 2022
(30)HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching
// 2021(CVPR)谷歌 轻量 经典 效果太好了(结果复现不出来?疑问?)
(31)Range‐free disparity estimation with self‐adaptive dual‐matching
// 2022
(32)Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks.
// 2021(AAAI)
(33)Deep Progressive Fusion Stereo Network
// 2021
(34)GwCNet:Group-wise Correlation Stereo Network
// 2020 (CVPR) “组相关” 经典
(35)CSPN:Learning Depth with Convolutional Spatial Propagation Network
// 2019 (TPAMI)
(36)Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy
// 2019 (TPAMI)
(37)Real-time self-adaptive deep stereo
// 2018
(38)NLCA-Net: a non-local context attention network for stereo matching
// 2020 (APSIPA)
(39)PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching
(40)Self-Supervised Multiscale Adversarial Regression Network for Stereo Disparity Estimation
// 2021
(41)Rethinking 3D Cost Aggregation in Stereo Matching
// 2023
(42)FADNet: A Fast and Accurate Network for Disparity Estimation
// 2020 (ICRA)
(43)A Normalized Disparity Loss for Stereo Matching Networks
// 2023 针对深度和视差分布不同
(44)Do End-to-end Stereo Algorithms Under-utilize Information?
// 2020 针对内容利用不充分和边缘过度平滑
(45)Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network
(46)RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching.
// 2022 (3D Vision Best Paper) 推荐
(47)CoEx:Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation.
// 2021 (CVPR)
(48)ACVNet: Attention Concatenation Volume for Accurate and Efficient Stereo Matching
// 2022 (CVPR) corr代价空间引导concat代价空间 推荐
(49)PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching
// 2022 (ECCV)金字塔融合+Warping代价
(50)CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching
// 2021 (CVPR)
(51)Degradation-agnostic Correspondence from Resolution-asymmetric Stereo
// 2022 特征度量一致性 特征度量损失 自增强策略
(52)CREStereo:Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation
// 2022 (CVPR)
(53)Iterative Geometry Encoding Volume for Stereo Matching
// 2023
(54)Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures
// 2020 (WACV)
(55)Anytime Stereo Image Depth Estimation on Mobile Devices
// 2019 (ICRA) 轻量网络 效果也没很好
(56)DecNet:A Decomposition Model for Stereo Matching
// 2021 (CVPR)轻量网络
(57)End-to-End Stereo Matching Network with Local Adaptive Awareness
// 2020
(58)MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching
// 2022 轻量级 (结合mobilenet)
(59)CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interaction
// 2023
(60)ACFNet:Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching
// 2020 (AAAI) 对CostVolume施加约束
(61)NLCA_Net_v2:Rethinking Training Strategy in Stereo Matching
// 2023 (TNNLS Q1) 轻量级
(62)SMD-Nets: Stereo Mixture Density Networks
// 2021 (CVPR) 恢复尖锐边界和高分辨率输出 双峰混合密度作为输出表示
(63)ChiTransformer: Towards Reliable Stereo from Cues
// 2022 (CVPR) 单目和和双目互补 自监督 Transformer
(64)SEDNet: Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation
// 2023 (CVPR) 不确定性估计 soft-histogramming KL散度
(65)Segstereo: Exploiting semantic information for disparity estimation
// 2018 (ECCV)DispNetC[13]、iResNet[14]和SegStereo,都在每个视差级别从两个视图提取的特征之间生成单通道相关性图,以损失特征表示中的结构和语义信息为代价来提高计算效率
(66)Depth Estimation by Combining Binocular Stereo and Monocular Structured-Light
// 2022 (CVPR) 双目 + 单目结构光
(67)NS-Stereo:NeRF-Supervised Deep Stereo
// 2023 (CVPR) NeRF + 自监督 , 采用NeRF生成左右三维信息,warp到中间位置(第三元位置),只用左右视图和NeRF生成的深度图训练网络,效果可比有监督方法!
(68)FCStereo:Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective
// 2022 (CVPR) 损失函数 域一致性 EPE : 0.86
(69)ADCPNet:Adaptive Disparity Candidates Prediction Network for Efficient Real-Time Stereo Matching
// 2020 (ARXIV) 2022(Q1) coarse-to-fine 轻量 自适应视差候选
(70)FoggyStereo: Stereo Matching with Fog Volume Representation
// 2022 (CVPR)雾天场景 鲁棒性
(71)RAG:Continual Stereo Matching of Continuous Driving Scenes with Growing Architecture
// 2022 (CVPR)持续学习 神经单元搜索 架构增长
(72)RTS2Net:Real-Time Semantic Stereo Matching
// 2020 (ICRA)图像语义分割+立体匹配 轻量级 粗到细 嵌入式
(73)Practical Deep Stereo(PDS): Toward applications-friendly deep stereo matching
// 2018 (NIPS)轻量网络
(74)BGNet:Bilateral Grid Learning for Stereo Matching Networks
// 2021 (CVPR)轻量网络 双边网格
(75)Unified Confidence Estimation Networks for Robust Stereo Matching
// 2021 置信度估计网络
(76)StereoScene: BEV-Assisted Stereo Matching Empowers 3D Semantic Scene Completion
// 2023 (arxiv)BEV辅助的立体匹配框架,用于3D语义场景补全
(77)DAFStereoNets:Do End-to-end Stereo Algorithms Under-utilize Information?
// 2021 (3DV) content-adaptive的滤波方式,从而更好地利用RGB的指导信息
(78)EAI-Stereo: Error Aware Iterative Network for Stereo Matching
// 2022 (ACCV) 误差感知细化模块 迭代多尺度宽式长短时记忆网络
(79)UCS-Net: Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness
// 2020 (CVPR)
// [阅读笔记](http://t.csdn.cn/BolqT "阅读笔记")
004 数据集
(1)A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
2015 (CVPR)SceneFlow数据集
(2)Are we ready for autonomous driving? the kitti vision benchmark suite.
2012 (CVPR)KITTI 2012数据集
(3)Joint 3d Estimation of Vehicles and Scene Flow
2015 (ISA) KITTI 2015数据集
(4)A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos
2017 (CVPR)ETH3D数据集
(5)High-resolution stereo datasets with subpixel-accurate ground truth.
2014 (GCPR) Middlebury dataset V3数据集

浙公网安备 33010602011771号