DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo
Open accessAbstract
In this paper, we introduce a local image descriptor, DAISY, which is very efficient to compute densely. We also present an EM-based algorithm to compute dense depth and occlusion maps from wide-baseline image pairs using this descriptor. This yields much better results in wide-baseline situations than the pixel and correlation-based algorithms that are commonly used in narrow-baseline stereo. Also, using a descriptor makes our algorithm robust against many photometric and geometric transformations. Our descriptor is inspired from earlier ones such as SIFT and GLOH but can be computed much faster for our purposes. Unlike SURF, which can also be computed efficiently at every pixel, it does not introduce artifacts that degrade the matching performance when used densely. It is important to note that our approach is the first algorithm that attempts to estimate dense depth maps from wide-baseline image pairs, and we show that it is a good one at that with many experiments for depth estimation accuracy, occlusion detection, and comparing it against other descriptors on laser-scanned ground truth scenes. We also tested our approach on a variety of indoor and outdoor scenes with different photometric and geometric transformations and our experiments support our claim to being robust against these.
Integrity signals
Registry
Cites
Statistics
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?
LIOP and DAISY are highly effective in recognition and classification due to their robustness to numerous variations and distortions.
“Meanwhile, local intensity order pattern (LIOP)36 and DAISY37 have been demonstrated as highly effective methods applied in the recognition and classification task due to their robustness to numerous variations and distortions.”
From Discriminative Learning for Automatic Staging of Placental Maturity via Multi-layer Fisher Vector (2015) · cites this paper as [37]
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · see citing works
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955 · see citing works
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916 · see citing works
Fast approximate energy minimization via graph cuts
Boykov, Y., Veksler, O., & Zabih, R. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.969114 · Cited by 6,988 · see citing works
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 · see citing works
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · see citing works
A Bayesian Hierarchical Model for Learning Natural Scene Categories
Fei-Fei, L., & Perona, P. (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.2005.16 · Cited by 3,657 · see citing works
A 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 · see citing works
Advances in computational stereo
Brown, M., Burschka, D., & Hager, G. D. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1217603 · Cited by 1,136 · see citing works
A stereo matching algorithm with an adaptive window: theory and experiment
Kanade, T., & Okutomi, M. (1994) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.310690 · Cited by 1,077 · see citing works
On benchmarking camera calibration and multi-view stereo for high resolution imagery
Strecha, C., von Hansen, W., Gool, L. V., Fua, P., & Thoennessen, U. (2008) · 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.2008.4587706 · Cited by 824 · see citing works
Self-citationBosch, A., Zisserman, A., & Muñoz, X. (2006) · Lecture notes in computer science · doi:10.1007/11744085_40 · Cited by 771 · see citing works
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 · see citing works
Integral histogram: a fast way to extract histograms in Cartesian spaces
Porikli, F. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.188 · Cited by 701 · see citing works
A pixel dissimilarity measure that is insensitive to image sampling
Birchfield, S. T., & Tomasi, C. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.677269 · Cited by 601 · see citing works
A 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 · see citing works
Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions
Tuytelaars, T., & Gool, L. V. (2000) · British Machine Vision Conference (BMVC) · doi:10.5244/c.14.38 · Cited by 451 · see citing works
Depth from edge and intensity based stereo
Baker, H. H., & Binford, T. O. (1981) · Defense Technical Information Center (DTIC) · Cited by 401 · see citing works
Learning Local Image Descriptors
Winder, S. A. J., & Brown, M. (2007) · 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.2007.382971 · Cited by 344 · see citing works
Geometric blur for template matching
Berg, A. C., & Malik, 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.2001.990529 · Cited by 280 · see citing works
Occlusions and binocular stereo
Geiger, D., Ladendorf, B., & Yuille, A. (1992) · Lecture notes in computer science · doi:10.1007/3-540-55426-2_48 · Cited by 246 · see citing works
Álvarez, L., Deriche, R., Sánchez, J., et al. (2002) · Journal of Visual Communication and Image Representation · doi:10.1006/jvci.2001.0482 · Cited by 197 · see citing works
Combined Depth and Outlier Estimation in Multi-View Stereo
Strecha, C., Fransens, R., & Gool, L. V. (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.2006.78 · Cited by 182 · see citing works
Complete dense stereovision using level set methods
Faugeras, O. D., & Keriven, R. (1998) · Lecture notes in computer science · doi:10.1007/bfb0055679 · Cited by 171 · see citing works
Disparity-space images and large occlusion stereo
INTILLE, S. S., & Bobick, A. (1994) · Lecture notes in computer science · doi:10.1007/bfb0028349 · Cited by 169 · see citing works
Occlusions and binocular stereo
Geiger, D., Ladendorf, B., & Yuille, A. (1995) · International Journal of Computer Vision · doi:10.1007/bf01679683 · Cited by 169 · see citing works
Dense matching of multiple wide-baseline views
Strecha, Tuytelaars, T., & Gool, V. (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238627 · Cited by 155 · see citing works
Computing differential properties of 3-D shapes from stereoscopic images without 3-D models
Devernay, F., & Faugeras (1994) · doi:10.1109/cvpr.1994.323831 · Cited by 150 · see citing works
Quam, L. H. (1987) · Elsevier eBooks · doi:10.1016/b978-0-08-051581-6.50015-5 · Cited by 126 · see citing works
3D modeling and rendering from multiple wide-baseline images by match propagation
Yao, J., & Cham, W.-K. (2006) · Signal Processing Image Communication · doi:10.1016/j.image.2006.03.005 · Cited by 18 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
LDAHash: Improved Matching with Smaller Descriptors
Strecha, C., Bronstein, A. M., Bronstein, M. M., & Fua, P. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.103 · Cited by 605 · see citing works
Self-citationSegmentation-Driven 6D Object Pose Estimation
Hu, Y., Hugonot, J., Fua, P., & Salzmann, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00350 · Cited by 333 · see citing works
Self-citationLocal Intensity Order Pattern for feature description
Wang, Z., Fan, B., & Wu, F. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126294 · Cited by 317 · see citing works
Learning visual feature descriptors for dynamic lighting conditions
Carlevaris-Bianco, N., & Eustice, R. M. (2014) · 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2014.6942941 · Cited by 75 · see citing works
Huang, S. H., Pan, J., Mulcaire, G., & Abbeel, P. (2015) · 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353475 · Cited by 39 · see citing works
Leveraging Mid-Level Semantic Boundary Cues for Automated Lymph Node Detection
Seff, A., Lu, L., Barbu, A., Roth, H., Shin, H.-C., & Summers, R. M. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-24571-3_7 · Cited by 36 · see citing works
Discriminative Learning for Automatic Staging of Placental Maturity via Multi-layer Fisher Vector
Lei, B., Yao, Y., Chen, S., Li, S., Li, W., Ni, D., & Wang, T. (2015) · Scientific Reports · doi:10.1038/srep12818 · Cited by 28 · see citing works
“Meanwhile, local intensity order pattern (LIOP)36 and DAISY37 have been demonstrated as highly effective methods applied in the recognition and classification task due to their robustness to numerous variations and distortions.”
MethodInfluentialOptical Flow Estimation with Deep Learning, a Survey on Recent Advances
Savian, S., Elahi, M., & Tillo, T. (2020) · Unsupervised and Semi-Supervised Learning · doi:10.1007/978-3-030-32583-1_12 · Cited by 29 · see citing works
A hierarchical feature selection strategy for deepfake video detection
Mohiuddin, S., Sheikh, K. H., Malakar, S., Velásquez, J. D., & Sarkar, R. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08201-z · Cited by 25 · see citing works
Neural Congealing: Aligning Images to a Joint Semantic Atlas
Ofri-Amar, D., Geyer, M., Kasten, Y., & Dekel, T. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01859 · Cited by 23 · see citing works
Illumination invariant feature point matching for high-resolution planetary remote sensing images
Wu, B., Zeng, H., & Hu, H. (2018) · Planetary and Space Science · doi:10.1016/j.pss.2018.01.007 · Cited by 20 · see citing works
Automatic staging of placental maturity based on dense descriptor
Li, X., Yao, Y., Ni, D., Chen, S., Li, S., Lei, B., & Wang, T. (2014) · Bio-Medical Materials and Engineering · doi:10.3233/bme-141100 · Cited by 12 · see citing works
Automatic placental maturity grading via hybrid learning
Lei, B., Tan, E.-L., Chen, S., Li, W., Ni, D., Yao, Y., & Wang, T. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.10.033 · Cited by 5 · see citing works
DilatedFormer: dilated granularity transformer network for placental maturity grading in ultrasound
Wu, Y., Yang, Y., Zhu, L., Han, Z., Luo, H., Xue, X., & Wang, W. (2023) · Frontiers in Physics · doi:10.3389/fphy.2023.1239400 · Cited by 2 · see citing works
- Authors
- Tola, E., Lepetit, V., & Fua, P.
- Affiliations
- École Polytechnique Fédérale de Lausanne (CH)
- ORCID
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2010-05
- Volume
- 32
- Issue
- 5
- Pages
- 815-830
- ISSN
- 0162-8828 (ISSN-L)
- OpenAlex
- W2104853049
- Cited by
- 1,405
- References
- 30
- Citations by year
- 2026: 18 · 2025: 39 · 2024: 64 · 2023: 61 · 2022: 72 · 2021: 84 · 2020: 102 · 2019: 117 · 2018: 100 · 2017: 126 · 2016: 139 · 2015: 136 · 2014: 120 · 2013: 93 · 2012: 55
- FWCI
- 49.23
- Type
- journal article
- Language
- en
- Open access
- green
- infoscience.epfl.ch
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Engineering › Aerospace Engineering › Robotics and Sensor-Based Localization
- Keywords
- DAISY descriptor, dense matching, wide-baseline stereo, dense depth estimation, occlusion detection, expectation-maximization algorithm, local image descriptors
- MeSH terms
- Algorithms, Artificial Intelligence, Image Interpretation, Computer-Assisted, Pattern Recognition, Automated, Photogrammetry, Subtraction Technique, Imaging, Three-Dimensional
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
