The DOI matches its Crossref record; 63 of the 70 references it cites were found in a registry or an index.
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms
Abstract
This paper presents a quantitative comparison of several multi-view stereo reconstruction algorithms. Until now, the lack of suitable calibrated multi-view image datasets with known ground truth (3D shape models) has prevented such direct comparisons. In this paper, we first survey multi-view stereo algorithms and compare them qualitatively using a taxonomy that differentiates their key properties. We then describe our process for acquiring and calibrating multiview image datasets with high-accuracy ground truth and introduce our evaluation methodology. Finally, we present the results of our quantitative comparison of state-of-the-art multi-view stereo reconstruction algorithms on six benchmark datasets. The datasets, evaluation details, and instructions for submitting new models are available online at http://vision.middlebury.edu/mview.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The presence of nonrigid or independent motion makes collecting a ground-truth dataset for optical flow far harder than for stereo, say, where structured light (Scharstein and Szeliski 2002) or range scanning (Seitz et al. 2006) can be used to obtain ground truth.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Seitz et al. 2006
In the citing paper
“We also compute robust accuracy measures similar to those in Seitz et al. (2006): A X denotes the accuracy of the error measure at the Xth percentile, after sorting the errors from low to high.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Seitz et al. (2006)
Citations
Cites
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
Scharstein, D., & Szeliski, R. (2002) · International Journal of Computer Vision · doi:10.1023/a:1014573219977 · Cited by 6,740
Self-citationA volumetric method for building complex models from range images
Curless, B., & Levoy, M. (1996) · Proceedings of the 23rd annual conference on Computer graphics and interactive techniques · doi:10.1145/237170.237269 · Cited by 3,124
Self-citationThe visual hull concept for silhouette-based image understanding
Laurentini, A. (1994) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.273735 · Cited by 1,470
High-quality video view interpolation using a layered representation
Zitnick, C. L., Kang, S. B., Uyttendaele, M., Winder, S. A. J., & Szeliski, R. (2004) · ACM Transactions on Graphics · doi:10.1145/1015706.1015766 · Cited by 1,386
Self-citationA Theory of Shape by Space Carving
Kutulakos, K. N., & Seitz, S. M. (2000) · International Journal of Computer Vision · doi:10.1023/a:1008191222954 · Cited by 1,281
Self-citationOkutomi, M., & Kanade, T. (1993) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.206955 · Cited by 948
Multi-camera Scene Reconstruction via Graph Cuts
Kolmogorov, V., & Ramin Zabih, A. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47977-5_6 · Cited by 745
Photorealistic Scene Reconstruction by Voxel Coloring
Seitz, S. M., & Dyer, C. R. (1999) · International Journal of Computer Vision · doi:10.1023/a:1008176507526 · Cited by 502
Self-citationA maximum-flow formulation of the N-camera stereo correspondence problem
Roy, S., & Cox, I. J. (2002) · International Conference on Computer Vision · doi:10.1109/iccv.1998.710763 · Cited by 489
Robust Parameter Estimation in Computer Vision
Stewart, C. V. (1999) · SIAM Review · doi:10.1137/s0036144598345802 · Cited by 455
Silhouette and stereo fusion for 3D object modeling
Esteban, C. H., & Schmitt, F. (2004) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2004.03.016 · Cited by 435
Surface light fields for 3D photography
Wood, D. N., Azuma, D. I., Aldinger, K., Curless, B., Duchamp, T., Salesin, D., & Stuetzle, W. (2000) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/344779.344925 · Cited by 430
Self-citationVariational principles, surface evolution, PDEs, level set methods, and the stereo problem
Faugeras, O. D., & Keriven, R. (1998) · IEEE Transactions on Image Processing · doi:10.1109/83.661183 · Cited by 429
Handling occlusions in dense multi-view stereo
Kang, S. B., Szeliski, R., & Chai, J. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2001.990462 · Cited by 359
Self-citationGoesele, M., Curless, B., & Seitz, S. M. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.199 · Cited by 331
Self-citationMulti-View Stereo via Volumetric Graph-Cuts
Vogiatzis, G., Torr, P. H. S., & Cipolla, R. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2005.238 · Cited by 279
Constructing virtual worlds using dense stereo
Narayanan, P. J., Rander, P. W., & Kanade, T. (2002) · International Conference on Computer Vision · doi:10.1109/iccv.1998.710694 · Cited by 265
Object-centered surface reconstruction: Combining multi-image stereo and shading
Fua, P., & Leclerc, Y. G. (1995) · International Journal of Computer Vision · doi:10.1007/bf01428192 · Cited by 248
Variational principles, surface evolution, PDE's, level set methods and the stereo problem
Faugeras, O. D., & Keriven, R. (2005) · doi:10.1109/ssbi.2002.1233990 · Cited by 248
A probabilistic framework for space carving
Broadhurst, A., Drummond, T. W., & Cipolla, R. (2002) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2001.937544 · Cited by 231
A Survey of Methods for Volumetric Scene Reconstruction from Photographs
Slabaugh, G., Schafer, R. W., Malzbender, T., & Culbertson, B. (2001) · Eurographics · doi:10.1007/978-3-7091-6756-4_6 · Cited by 197
Chen, W.-C., Bouguet, J.-Y., Chu, M. H., & Grzeszczuk, R. (2002) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/566570.566601 · Cited by 172
Stereo Matching with Transparency and Matting
Szeliski, R., & Golland, P. (1999) · International Journal of Computer Vision · doi:10.1023/a:1008192912624 · Cited by 165
Self-citationVolumetric Scene Reconstruction from Multiple Views
Dyer, C. R. (2001) · Springer eBooks · doi:10.1007/978-1-4615-1529-6_16 · Cited by 157
Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance
Jin, H., Soatto, S., & Yezzi, A. J. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-6876-7 · Cited by 137
Sinha, S. N., & Pollefeys, M. (2005) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2005.159 · Cited by 135
Representing stereo data with the Delaunay triangulation
Faugeras, O. D., Bras-Mehlman, E. L., & Boissonnat, J. D. (1990) · Artificial Intelligence · doi:10.1016/0004-3702(90)90098-k · Cited by 122
Prediction error as a quality metric for motion and stereo
Szeliski, R. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790301 · Cited by 118
Self-citationModelling Dynamic Scenes by Registering Multi-View Image Sequences
Pons, J.-P., Keriven, R., & Faugeras, O. D. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2005.227 · Cited by 111
Chen, W.-C., Bouguet, J.-Y., Chu, M. H., & Grzeszczuk, R. (2002) · ACM Transactions on Graphics · doi:10.1145/566654.566601 · Cited by 108
Multi-view stereo beyond Lambert
Jin, H., Soatto, S., & Yezzi, A. J. (2003) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2003.1211351 · Cited by 105
Methods for Volumetric Reconstruction of Visual Scenes
Slabaugh, G., Culbertson, W. B., Malzbender, T., Stevens, M. R., & Schafer, R. W. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013093.45070.3b · Cited by 103
Image-consistent surface triangulation
Morris, D., & Takeo Kanade, A. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2000.855837 · Cited by 102
A Bayesian method for probable surface reconstruction and decimation
Diebel, J. R., Thrun, S., & Brünig, M. (2006) · ACM Transactions on Graphics · doi:10.1145/1122501.1122504 · Cited by 101
Self-citationKutulakos, K. N. (2000) · Lecture notes in computer science · doi:10.1007/3-540-45054-8_5 · Cited by 97
Voxel carving for specular surfaces
Bonfort, & Sturm (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238401 · Cited by 97
Bayesian 3D Modeling from Images Using Multiple Depth Maps
Gargallo, P., & Sturm, P. F. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2005.84 · Cited by 96
Shape reconstruction in projective grid space from large number of images
Saitô, H., & Kanade, T. (2003) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1999.784607 · Cited by 93
Shape Reconstruction from 3D and 2D Data Using PDE-Based Deformable Surfaces
Duan, Y., Liu, Y., Qin, H., & Samaras, D. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24672-5_19 · Cited by 91
Yang, R., Pollefeys, M., & Welch, G. (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238399 · Cited by 73
A multi-view approach to motion and stereo
Szeliski, R. (2003) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1999.786933 · Cited by 68
Self-citationMulti-hypothesis, volumetric reconstruction of 3-D objects from multiple calibrated camera views
Eisert, P., Steinbach, E. G., & Girod, B. (1999) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1999.757599 · Cited by 63
Poxels: Probabilistic Voxelized Volume Reconstruction
Bonet, J. S. D. (1999) · Cited by 63
Example-Based Stereo with General BRDFs
Treuille, A., Hertzmann, A., & Seitz, S. M. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24671-8_36 · Cited by 62
Self-citationTales of shape and radiance in multiview stereo
Soatto, S., Yezzi, A. J., & Jin, H. (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238454 · Cited by 62
Isidoro, J. R., & Sclaroff, S. (2003) · Cited by 55
A Probabilistic Theory of Occupancy and Emptiness
Bhotika, R., Fleet, D. J., & Kutulakos, K. N. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47977-5_8 · Cited by 52
Isidro, & Sclaroff (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238645 · Cited by 49
Surface reconstruction from feature based stereo
Taylor (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238338 · Cited by 47
Savarese, S., Rushmeier, H., Bernardini, F., & Perona, P. (2002) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2001.937517 · Cited by 39
Three-dimensional object reconstruction from two-dimensional images
Rockwood, A. P., & Winget, J. (1997) · Computer-Aided Design · doi:10.1016/s0010-4485(96)00056-5 · Cited by 35
When is the shape of a scene unique given its light-field: a fundamental theorem of 3D vision?
Baker, S., Sim, T., & Takeo Kanade, A. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1159949 · Cited by 30
Reconstruction of scene models from sparse 3D structure
Manessis, A., Hilton, A., Palmer, P. L., McLauchlan, P. F., & Shen, X. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2000.854938 · Cited by 30
Variational Stereovision and 3D Scene Flow Estimation with Statistical Similarity Measures
Pons, J.-P., Keriven, R., Faugeras, O. D., & Hermosillo, G. (2003) · Cited by 28
Variational stereovision and 3D scene flow estimation with statistical similarity measures
Pons, Keriven, Faugeras, & Hermosillo (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238402 · Cited by 28
Progressive surface reconstruction from images using a local prior
Zeng, G., Paris, S., Quan, L., & Sillion, F. X. (2005) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2005.196 · Cited by 26
High-fidelity image-based modeling
Ponce, J., & Furukawa, Y. (2008) · Cited by 23
Geo-Consistency for Wide Multi-Camera Stereo
Drouin, M.-A., Trudeau, M., & Roy, S. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2005.168 · Cited by 22
Shape and View Independent Reflectance Map from Multiple Views
Yu, T., Xu, N., & Ahuja, N. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24673-2_48 · Cited by 18
Reconstructing relief surfaces
Vogiatzis, G., Torr, P. H. S., Seitz, S. M., & Cipolla, R. (2007) · Image and Vision Computing · doi:10.1016/j.imavis.2007.01.006 · Cited by 18
Self-citationImproved Voxel Coloring Via Volumetric Optimization
Slabaugh, G., Malzbender, T., Culbertson, W. B., & Schafer, R. W. (2001) · Cited by 18
Reconstructing Relief Surfaces
Vogiatzis, G., Torr, P. H. S., Seitz, S. M., & Cipolla, R. (2004) · British Machine Vision Conference (BMVC) · doi:10.5244/c.18.14 · Cited by 13
Self-citationHigher-order nonlinear priors for surface reconstruction
Taşdizen, T., & Whitaker, R. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.31 · Cited by 10
Flagged first, then by citations
7 of the 70 references couldn’t be matched to a known paper.
Research works printed but not linked: 5
- zhang, 2001, Image-based multiresolution shape recovery by surface deformation, Videometrics Opt Meth 3D Shape Meas, 51
- seitz, 0, Multi-view Stereo Evaluation Web Page
- fromherz, 1995, Shape from multiple cues: Integrating local brightness information, ICYCS
- bouguet, 0, Camera Calibration Toolbox for MATLAB
- prock, 1998, Towards real-time voxel coloring, Image Understanding WS, 315
Cited by
Sorted by citations
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
KinectFusion: Real-time dense surface mapping and tracking
Newcombe, R. A., Fitzgibbon, A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A. J., Kohi, P., Shotton, J., & Hodges, S. (2011) · 2011 10th IEEE International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2011.6092378 · Cited by 4,008
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
Park, J. J., Florence, P., Straub, J., Newcombe, R., & Lovegrove, S. J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00025 · Cited by 3,789
Accurate, Dense, and Robust Multiview Stereopsis
Furukawa, Y., & Ponce, J. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.161 · Cited by 3,031
Pixelwise View Selection for Unstructured Multi-View Stereo
Schönberger, J. L., Zheng, E., Frahm, J., & Pollefeys, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46487-9_31 · Cited by 2,331
Metadata
- Authors
- Seitz, S. M., Curless, B., Diebel, J., Scharstein, D., & Szeliski, R.
- Affiliations
- University of Washington (US)
- Stanford University (US)
- Middlebury College (US)
- Microsoft Research (United Kingdom) (GB)
- Venue
- 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR'06)
- Publisher
- IEEE
- Published
- 2006-07-10
- Volume
- 1
- Pages
- 519-528
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2160014001
- Cited by
- 2,457
- References
- 70
- Citations by year
- 2026: 60 · 2025: 94 · 2024: 118 · 2023: 131 · 2022: 94 · 2021: 142 · 2020: 134 · 2019: 129 · 2018: 116 · 2017: 150 · 2016: 146 · 2015: 149 · 2014: 177 · 2013: 151 · 2012: 157
- FWCI
- 70.73
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
- Keywords
- multi-view stereo, 3D reconstruction, algorithm comparison, camera calibration, benchmark dataset, quantitative evaluation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
