The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
On the spatial statistics of optical flow
Abstract
We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natural scenes and 3D camera motions recovered from handheld and car-mounted video sequences. A detailed analysis of optical flow statistics in natural scenes is presented and machine learning methods are developed to learn a Markov random field model of optical flow. The prior probability of a flow field is formulated as a field-of-experts model that captures the higher order spatial statistics in overlapping patches and is trained using contrastive divergence. This new optical flow prior is compared with previous robust priors and is incorporated into a recent, accurate algorithm for dense optical flow computation. Experiments with natural and synthetic sequences illustrate how the learned optical flow prior quantitatively improves flow accuracy and how it captures the rich spatial structure found in natural scene motion.
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
“For example, the authors of [33] developed a limited model exhibiting regularities, but only under the assumption that the camera is in motion, yet no objects in the imaged scene move independently.”
From Blind Prediction of Natural Video Quality (2014) · cites this paper as [33]
Citations
Cites
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879
Flagged first, then by citations
Research works printed but not linked: 27
- 10.1109/ICCV.1999.791283 · DOI
- huang, 2000, Statistics of Natural Images and Models
- huang, 2000, Statistics of range images, CVPR, 1, 1324
- 10.1016/0004-3702(81)90024-2 · DOI · Paper page
- golub, 1996, Matrix Computations
- 10.1109/34.250841 · DOI
- 10.1023/A:1008156202475 · DOI
- fleet, 2002, Bayesian inference of visual motion boundaries, Exploring Artificial Intelligence in the New Millennium
- 10.1109/ICCV.2001.937655 · DOI · Paper page
- konrad, 1988, Multigrid Bayesian estimation of image motion fields using stochastic relaxation, ICCV, 354
- 10.1109/TPAMI.1987.4767896 · DOI
- ross, 2003, A systematic approach to learning object segmentation from motion, NIPS 2003 Workshop on Open Challenges in Cognitive Vision
- 10.1109/CVPR.2005.160 · DOI
- 10.1109/CVPR.1991.139707 · DOI
- 10.1162/jmlr.2003.4.7-8.1235 · DOI
- 10.1098/rspb.1998.0577 · DOI
- weiss, 1998, Slow and smooth: A Bayesian theory for the combination of local motion signals in human vision, MIT AI Memo, 1624
- zhu, 1997, Prior learning and Gibbs reaction-diffusion, PAMI, 19, 1236, 10.1109/34.632983 · DOI
- 10.1007/BF01420984 · DOI · Paper page
- 10.1006/cviu.2000.0900 · DOI
- 0, Brown range image database
- 10.1023/B:VISI.0000045324.43199.43 · DOI · Paper page
- 10.1006/cviu.1996.0006 · DOI
- 10.1109/CVPR.1991.139705 · DOI
- 10.1007/s00422-003-0434-6 · DOI
- 10.1109/CVPR.2001.990516 · DOI
- calow, 2004, Statistics of optic flow for self-motion through natural scenes, Dynamic Perception, 133
Cited by
Sorted by citations
Blind Prediction of Natural Video Quality
Saad, M. A., Bovik, A. C., & Charrier, C. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2299154 · Cited by 471
Metadata
- Authors
- Roth, S., & Black, M. J.
- Affiliations
- Brown University (US)
- ORCID
- Roth, S.
- Venue
- Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
- Publisher
- IEEE
- Published
- 2005
- Pages
- 42-49 Vol. 1
- OpenAlex
- W2130159466
- Cited by
- 95
- References
- 1
- Citations by year
- 2022: 1 · 2021: 2 · 2020: 2 · 2019: 1 · 2018: 3 · 2016: 4 · 2015: 7 · 2014: 8 · 2013: 5 · 2012: 9
- FWCI
- 8.58
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Stabilization
- Keywords
- optical flow, spatial statistics, Markov random fields, dense optical flow, depth images, contrastive divergence, synthetic training data
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
