CVLab dense multi-view stereo image database,
2010
HTML Version.
Dataset, Stereo.
Multiple views, ground level, of buildings
IS-3D: Data,
2008.
HTML Version.
Dataset, Stereo. Multiple views of various structures.
Project Photofly,
2010
WWW Link.
Vendor, 3-D Models.
Automatically converting photographs shot around an object or a scene
into photo scenes.
See also Autodesk.
Aliaga, D.G.[Daniel G.],
Funkhouser, T.[Thomas],
Yanovsky, D.[Dimah], and
Carlbom, I.[Ingrid],
Sea of Images: A Dense Sampling Approach
for Rendering Large Indoor Environments,
IEEE_CGA(23), No. 6, November/December, 2003, pp. 22-30.
HTML Version.
See also Accurate Catadioptric Calibration for Real-time Pose Estimation of Room-size Environments.
BibRef
0311
Brandt, S.S.[Sami S.],
Conditional solutions for the affine reconstruction of N-views,
IVC(23), No. 7, 1 July 2005, pp. 619-630.
Elsevier DOI
0506
BibRef
Kannala, J.H.[Ju-Ho],
Rahtu, E.[Esa],
Brandt, S.S.[Sami S.],
Heikkila, J.[Janne],
Object recognition and segmentation by non-rigid quasi-dense matching,
CVPR08(1-8).
IEEE DOI
0806
BibRef
Koskenkorva, P.[Pekka],
Kannala, J.H.[Ju-Ho],
Brandt, S.S.[Sami S.],
Quasi-dense Wide Baseline Matching for Three Views,
ICPR10(806-809).
IEEE DOI
1008
BibRef
Earlier: A2, A3, Only:
Quasi-Dense Wide Baseline Matching Using Match Propagation,
CVPR07(1-8).
IEEE DOI
0706
BibRef
Lazebnik, S.[Svetlana],
Furukawa, Y.[Yasutaka],
Ponce, J.[Jean],
Projective Visual Hulls,
IJCV(74), No. 2, August 2007, pp. 137-165.
Springer DOI
PDF File.
0705
For data:
See also University of Illinois Datasets.
BibRef
Lazebnik, S.[Svetlana],
Boyer, E.[Edmond],
Ponce, J.[Jean],
On Computing Exact Visual Hulls of Solids Bounded by Smooth Surfaces,
CVPR01(I:156-161).
IEEE DOI
PS File.
0110
Contours and shape of visual cone.
BibRef
Shan, Q.[Qi],
Adams, R.,
Curless, B.,
Furukawa, Y.,
Seitz, S.M.,
The Visual Turing Test for Scene Reconstruction,
3DV13(25-32)
IEEE DOI
1311
data visualisation
BibRef
Furukawa, Y.[Yasutaka],
Curless, B.[Brian],
Seitz, S.M.[Steven M.],
Szeliski, R.S.[Richard S.],
Towards Internet-scale multi-view stereo,
CVPR10(1434-1441).
IEEE DOI
1006
BibRef
Furukawa, Y.[Yasutaka],
Curless, B.[Brian],
Seitz, S.M.[Steven M.],
Szeliski, R.S.[Richard S.],
Manhattan-world stereo,
CVPR09(1422-1429).
IEEE DOI
0906
BibRef
Furukawa, Y.[Yasutaka],
Ponce, J.[Jean],
Accurate, Dense, and Robust Multiview Stereopsis,
PAMI(32), No. 8, August 2010, pp. 1362-1376.
IEEE DOI
1007
BibRef
Earlier:
Accurate, Dense, and Robust Multi-View Stereopsis,
CVPR07(1-8).
IEEE DOI
0706
Award, Longuet-Higgins. (after 10 years).
Dense set of small rectangular patches covering visible surfaces.
Match, expand, filter, start from sparse set of matches.
See also Robust Structure and Motion from Outlines of Smooth Curved Surfaces.
BibRef
Snavely, N.[Noah],
Seitz, S.M.[Steven M.],
Szeliski, R.S.[Richard S.],
Modeling the World from Internet Photo Collections,
IJCV(80), No. 2, November 2008, pp. xx-yy.
Springer DOI
0809
BibRef
Earlier:
Photo Tourism: Exploring image collections in 3D,
SigGraph06(835-846).
PDF File. For browsing large image collections.
See also Fast algorithms for L-inf problems in multiview geometry.
BibRef
Snavely, N.[Noah],
Seitz, S.M.[Steven M.],
Szeliski, R.S.[Richard S.],
Skeletal graphs for efficient structure from motion,
CVPR08(1-8).
IEEE DOI
WWW Link.
0806
BibRef
Wilson, K.[Kyle],
Snavely, N.[Noah],
Robust Global Translations with 1DSfM,
ECCV14(III: 61-75).
Springer DOI
1408
BibRef
Snavely, N.[Noah],
Bundler: Structure from Motion for Unordered Image Collections,
OnlineMay 2009.
Code, Structure from Motion.
WWW Link.
0909
BibRef
Simon, I.[Ian],
Snavely, N.[Noah],
Seitz, S.M.[Steven M.],
Scene Summarization for Online Image Collections,
ICCV07(1-8).
IEEE DOI
WWW Link.
0710
Combine images using a Shape from Motion scheme to map where the camera is.
See also Multi-View Stereo for Community Photo Collections.
BibRef
Snavely, N.[Noah],
Garg, R.[Rahul],
Seitz, S.M.[Steven M.],
Szeliski, R.[Richard],
Finding Paths through the World's Photos,
SIGGraph-08(xx-yy)
PDF File.
WWW Link.
BibRef
0800
Crandall, D.J.[David J.],
Snavely, N.[Noah],
Modeling People and Places with Internet Photo Collections,
CACM(55), No. 6, June 2012, pp. 52-60.
DOI Link
1205
Understanding the world from the sea of online photos.
BibRef
Vu, H.H.[Hoang-Hiep],
Labatut, P.[Patrick],
Pons, J.P.[Jean-Philippe],
Keriven, R.[Renaud],
High Accuracy and Visibility-Consistent Dense Multiview Stereo,
PAMI(34), No. 5, May 2012, pp. 889-901.
IEEE DOI
1204
BibRef
Earlier: A1, A4, A2, A3:
Towards high-resolution large-scale multi-view stereo,
CVPR09(1430-1437).
IEEE DOI
0906
See also Fast Level Set Multi-View Stereo on Graphics Hardware. Complete, multi-view with uncontrolled imaging (outdoor) conditions.
Compare to:
See also CVLab dense multi-view stereo image database.
BibRef
Labatut, P.[Patrick],
Pons, J.P.[Jean-Philippe],
Keriven, R.[Renaud],
Hierarchical shape-based surface reconstruction for dense multi-view
stereo,
3DIM09(1598-1605).
IEEE DOI
0910
See also Fast Level Set Multi-View Stereo on Graphics Hardware.
BibRef
Tola, E.[Engin],
Strecha, C.[Christoph],
Fua, P.[Pascal],
Efficient large-scale multi-view stereo for ultra high-resolution image
sets,
MVA(23), No. 5, September 2012, pp. 903-920.
WWW Link.
1208
See also Combined Depth and Outlier Estimation in Multi-View Stereo.
See also On benchmarking camera calibration and multi-view stereo for high resolution imagery.
BibRef
Steve Seitz: Using 2D images to create 3D models of historic places,
SPIE(Newsroom), January 22, 2013
DOI Link
1305
Those photos you took on your vacation may well have contributed to an
impressive 3D model of a familiar tourist attraction.
BibRef
Qian, X.,
Xue, Y.,
Yang, X.,
Tang, Y.Y.,
Hou, X.,
Mei, T.,
Landmark Summarization With Diverse Viewpoints,
CirSysVideo(25), No. 11, November 2015, pp. 1857-1869.
IEEE DOI
1511
Bit error rate
BibRef
Xue, B.D.[Bin-Dang],
Cao, L.[Lei],
Han, D.H.[Dong-Hai],
Bai, X.Z.[Xiang-Zhi],
Zhou, F.[Fugen],
Jiang, Z.G.[Zhi-Guo],
A DAISY descriptor based multi-view stereo method for large-scale
scenes,
JVCIR(35), No. 1, 2016, pp. 15-24.
Elsevier DOI
1602
Computer vision
BibRef
Xiao, X.W.[Xiong-Wu],
Guo, B.X.[Bing-Xuan],
Li, D.R.[De-Ren],
Li, L.H.[Lin-Hui],
Yang, N.[Nan],
Liu, J.C.[Jian-Chen],
Zhang, P.[Peng],
Peng, Z.[Zhe],
Multi-View Stereo Matching Based on Self-Adaptive Patch and Image
Grouping for Multiple Unmanned Aerial Vehicle Imagery,
RS(8), No. 2, 2016, pp. 89.
DOI Link
1603
BibRef
Martin-Brualla, R.[Ricardo],
Gallup, D.[David],
Seitz, S.M.[Steven M.],
3D Time-Lapse Reconstruction from Internet Photos,
IJCV(125), No. 1-3, December 2018, pp. 52-64.
Springer DOI
1711
BibRef
Earlier:
ICCV15(1332-1340)
IEEE DOI
1602
3D Times lapse video from a photo collection of a landmark.
Cameras. Not just 3D, but change over time. Large number of images.
BibRef
Ben-Ezra, S.[Shahar],
Cohen-Or, D.[Daniel],
Space-time image layout,
VC(34), No. 3, March 2018, pp. 417-430.
Springer DOI
1802
Activity captured by multiple people.
BibRef
Joo, H.[Hanbyul],
Simon, T.[Tomas],
Li, X.L.[Xu-Long],
Liu, H.[Hao],
Tan, L.[Lei],
Gui, L.[Lin],
Banerjee, S.[Sean],
Godisart, T.[Timothy],
Nabbe, B.[Bart],
Matthews, I.[Iain],
Kanade, T.[Takeo],
Nobuhara, S.[Shohei],
Sheikh, Y.[Yaser],
Panoptic Studio: A Massively Multiview System for Social Interaction
Capture,
PAMI(41), No. 1, January 2019, pp. 190-204.
IEEE DOI
1812
BibRef
Earlier: A1, A4, A5, A6, A9, A10, A11, A11, A12, Only:
Panoptic Studio:
A Massively Multiview System for Social Motion Capture,
ICCV15(3334-3342)
IEEE DOI
1602
Cameras, Sensors, Face,
High definition video, Motion measurement, Human motion capture,
markerless motion capture
BibRef
Zhang, R.Z.[Run-Ze],
Zhu, S.Y.[Si-Yu],
Shen, T.W.[Tian-Wei],
Zhou, L.[Lei],
Luo, Z.X.[Zi-Xin],
Fang, T.[Tian],
Quan, L.[Long],
Distributed Very Large Scale Bundle Adjustment by Global Camera
Consensus,
PAMI(42), No. 2, February 2020, pp. 291-303.
IEEE DOI
2001
BibRef
Earlier: A1, A2, A6, A7, Only:
ICCV17(29-38)
IEEE DOI
1802
Cameras, Bundle adjustment, Optimization, Convex functions,
Convergence, Merging, Bundle adjustment, structure-from-motion,
distributed computing.
distributed processing, graph theory,
image motion analysis.
BibRef
Zhang, R.Z.,
Li, S.W.,
Fang, T.,
Zhu, S.Y.,
Quan, L.,
Joint Camera Clustering and Surface Segmentation for Large-Scale
Multi-view Stereo,
ICCV15(2084-2092)
IEEE DOI
1602
Cameras
BibRef
Li, S.W.[Shi-Wei],
Siu, S.Y.[Sing Yu],
Fang, T.[Tian],
Quan, L.[Long],
Efficient Multi-view Surface Refinement with Adaptive Resolution
Control,
ECCV16(I: 349-364).
Springer DOI
1611
BibRef
Zhu, S.Y.,
Zhang, R.Z.,
Zhou, L.,
Shen, T.,
Fang, T.,
Tan, P.,
Quan, L.,
Very Large-Scale Global SfM by Distributed Motion Averaging,
CVPR18(4568-4577)
IEEE DOI
1812
Cameras, Particle separators,
Image reconstruction, Computer vision, Convergence, Robustness
BibRef
Parisotto, S.,
Calatroni, L.,
Bugeau, A.,
Papadakis, N.,
Schönlieb, C.B.,
Variational Osmosis for Non-Linear Image Fusion,
IP(29), 2020, pp. 5507-5516.
IEEE DOI
2005
Osmosis filtering, image fusion, non-convex optimization,
primal-dual algorithm, cultural heritage imaging
BibRef
Li, Z.,
Zuo, W.,
Wang, Z.,
Zhang, L.,
Confidence-Based Large-Scale Dense Multi-View Stereo,
IP(29), 2020, pp. 7176-7191.
IEEE DOI
2007
Image reconstruction, Surface reconstruction,
Interpolation, Estimation,
refinement
BibRef
Nassar, A.S.[Ahmed Samy],
Lefčvre, S.[Sébastien],
Wegner, J.D.[Jan Dirk],
Multi-View Instance Matching with Learned Geometric Soft-Constraints,
IJGI(9), No. 11, 2020, pp. xx-yy.
DOI Link
2012
VArious multiple views of objects for detailed descriptions.
BibRef
Xu, Z.,
Liu, Y.,
Shi, X.,
Wang, Y.,
Zheng, Y.,
MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient
Large Scale Scene Reconstruction,
CVPR20(5980-5989)
IEEE DOI
2008
Geometry, Image reconstruction,
Merging, Benchmark testing, Image matching, Surface texture
BibRef
Yu, Z.,
Gao, S.,
Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned
Propagation and Gauss-Newton Refinement,
CVPR20(1946-1955)
IEEE DOI
2008
Memory management, Image resolution,
Prediction algorithms, Image reconstruction, Optimization, Feature extraction
BibRef
Yao, Y.,
Luo, Z.,
Li, S.,
Zhang, J.,
Ren, Y.,
Zhou, L.,
Fang, T.,
Quan, L.,
BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo
Networks,
CVPR20(1787-1796)
IEEE DOI
2008
Training, Lighting, Cameras,
Image reconstruction, Pipelines, Benchmark testing
BibRef
Wang, Y.,
Guan, T.,
Chen, Z.,
Luo, Y.,
Luo, K.,
Ju, L.,
Mesh-Guided Multi-View Stereo With Pyramid Architecture,
CVPR20(2036-2045)
IEEE DOI
2008
Image reconstruction, Fuses, Face,
Surface treatment, Geometry, Estimation
BibRef
Gu, X.,
Fan, Z.,
Zhu, S.,
Dai, Z.,
Tan, F.,
Tan, P.,
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo
Matching,
CVPR20(2492-2501)
IEEE DOI
2008
Graphics processing units,
Feature extraction, Standards, Cameras, Spatial resolution
BibRef
Yang, J.,
Mao, W.,
Alvarez, J.M.,
Liu, M.,
Cost Volume Pyramid Based Depth Inference for Multi-View Stereo,
CVPR20(4876-4885)
IEEE DOI
2008
Image resolution, Feature extraction,
Buildings, Memory management, Estimation, Image reconstruction
BibRef
Bai, Z.,
Cui, Z.,
Rahim, J.A.,
Liu, X.,
Tan, P.,
Deep Facial Non-Rigid Multi-View Stereo,
CVPR20(5849-5859)
IEEE DOI
2008
Face, Optimization, Image reconstruction,
Adaptation models, Shape, Geometry
BibRef
Liu, J.,
Ji, S.,
A Novel Recurrent Encoder-Decoder Structure for Large-Scale
Multi-View Stereo Reconstruction From an Open Aerial Dataset,
CVPR20(6049-6058)
IEEE DOI
2008
Image reconstruction, Cameras,
Surface reconstruction, Machine learning, Memory management, Buildings
BibRef
Henzler, P.[Philipp],
Mitra, N.[Niloy],
Ritschel, T.[Tobias],
Escaping Plato's Cave: 3D Shape From Adversarial Rendering,
ICCV19(9983-9992)
IEEE DOI
2004
3D from unstructured collection of 2D images.
image reconstruction, neural nets, rendering (computer graphics),
stereo image processing, 3D shape, adversarial rendering,
Image reconstruction
BibRef
Maset, E.[Eleonora],
Arrigoni, F.[Federica],
Fusiello, A.[Andrea],
Practical and Efficient Multi-view Matching,
ICCV17(4578-4586)
IEEE DOI
1802
BibRef
Earlier: A2, A1, A3:
Synchronization in the Symmetric Inverse Semigroup,
CIAP17(II:70-81).
Springer DOI
1711
image denoising, image matching, iterative methods,
closed-form efficiency algorithm, iterative techniques,
Matrix decomposition.
Sequence of multiple images.
BibRef
Radenovic, F.[Filip],
Schönberger, J.L.[Johannes L.],
Ji, D.H.[Ding-Huang],
Frahm, J.M.[Jan-Michael],
Chum, O.[Ondrej],
Matas, J.G.[Jirí G.],
From Dusk Till Dawn: Modeling in the Dark,
CVPR16(5488-5496)
IEEE DOI
1612
BibRef
Bláha, M.[Maro],
Vogel, C.[Christoph],
Richard, A.[Audrey],
Wegner, J.D.[Jan D.],
Pock, T.[Thomas],
Schindler, K.[Konrad],
Large-Scale Semantic 3D Reconstruction:
An Adaptive Multi-resolution Model for Multi-class Volumetric Labeling,
CVPR16(3176-3184)
IEEE DOI
1612
BibRef
Dar, M.[Mor],
Moses, Y.[Yael],
Temporal Epipolar Regions,
CVPR16(1220-1228)
IEEE DOI
1612
Dynamic events from multiple unconstrained viewpoints.
BibRef
Zhuo, W.,
Salzmann, M.[Mathieu],
He, X.M.[Xu-Ming],
Liu, M.M.[Miao-Miao],
Indoor Scene Parsing with Instance Segmentation, Semantic Labeling
and Support Relationship Inference,
CVPR17(6269-6277)
IEEE DOI
1711
BibRef
Earlier: A4, A3, A2, Only:
Building Scene Models by Completing and Hallucinating Depth and
Semantics,
ECCV16(VI: 258-274).
Springer DOI
1611
Cognition, Image segmentation, Labeling, Semantics,
Support vector machines.
Occlusions in depth sensing.
BibRef
Diaz, R.,
Lee, M.,
Schubert, J.,
Fowlkes, C.C.,
Lifting GIS maps into strong geometric context for scene
understanding,
WACV16(1-9)
IEEE DOI
1606
Combine GIS resource with large sets of images using shape from motion
techniques.
BibRef
Locher, A.,
Perdoch, M.,
Van Gool, L.J.,
Progressive Prioritized Multi-view Stereo,
CVPR16(3244-3252)
IEEE DOI
1612
BibRef
Locher, A.,
Perdoch, M.,
Riemenschneider, H.,
Van Gool, L.J.,
Mobile phone and cloud: A dream team for 3D reconstruction,
WACV16(1-8)
IEEE DOI
1606
Image reconstruction
BibRef
Ji, D.H.[Ding-Huang],
Dunn, E.[Enrique],
Frahm, J.M.[Jan-Michael],
Synthesizing Illumination Mosaics from Internet Photo-Collections,
ICCV15(3988-3996)
IEEE DOI
1602
Feature extraction
BibRef
Galliani, S.[Silvano],
Schindler, K.[Konrad],
Just Look at the Image: Viewpoint-Specific Surface Normal Prediction
for Improved Multi-View Reconstruction,
CVPR16(5479-5487)
IEEE DOI
1612
BibRef
Galliani, S.,
Lasinger, K.,
Schindler, K.,
Massively Parallel Multiview Stereopsis by Surface Normal Diffusion,
ICCV15(873-881)
IEEE DOI
1602
Benchmark testing
BibRef
Peres, M.,
Savakis, A.,
Crowdpainting with Light: Participatory Imaging at the Big Shot,
Extreme15(683-687)
IEEE DOI
1602
Buildings
BibRef
Chen, Y.C.,
Tseng, Y.H.,
Hsieh, C.Y.,
Wang, P.C.,
Tsai, P.C.,
Object-space Multi-image Matching of Mobile-mapping-system Image
Sequences,
ISPRS12(XXXIX-B5:465-470).
DOI Link
1209
BibRef
Abate, D.,
Furini, G.,
Migliori, S.,
Pierattini, S.,
Project Photofly:
New 3D Modeling Online Web Service (Case Studies and Assessments),
3DARCH11(xx-yy).
PDF File.
1103
See also Project Photofly.
BibRef
Martinec, D.[Daniel],
Pajdla, T.[Tomas],
Robust Rotation and Translation Estimation in Multiview Reconstruction,
CVPR07(1-8).
IEEE DOI
0706
BibRef
Martinec, D.[Daniel],
Pajdla, T.[Tomás],
3D Reconstruction by Gluing Pair-Wise Euclidean Reconstructions, or
'How to Achieve a Good Reconstruction from Bad Images',
3DPVT06(25-32).
IEEE DOI
0606
BibRef
Earlier:
3D Reconstruction by Fitting Low-Rank Matrices with Missing Data,
CVPR05(I: 198-205).
IEEE DOI
0507
BibRef
Earlier:
Line reconstruction from many perspective images by factorization,
CVPR03(I: 497-502).
IEEE DOI
0307
BibRef
Earlier:
Consistent Multi-view Reconstruction from Epipolar Geometries with
Outliers,
SCIA03(493-500).
Springer DOI
0310
BibRef
Earlier:
Outlier Detection for Factorization-Based Reconstruction from
Perspective Images with Occlusions,
PCV02(B: 161).
0305
BibRef
And:
Structure from Many Perspective Images with Occlusions,
ECCV02(II: 355 ff.).
Springer DOI
0205
3D from many views.
BibRef
Ollis, M.[Mark],
Malaxos, D.[David],
3D Video Capture, Reconstruction, and Viewing Systems,
CVPR01(Demos 2-3).
0110
Many cameras.
BibRef
Chapter on Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular continues in
Multi-Baseline Stereo, Multibaseline Stereo .