CoChat
Sign Up
Cited by 618Advanced Vision and ImagingVideo Surveillance and Tracking MethodsVideo Coding and Compression Technologies

A Database and Evaluation Methodology for Optical Flow

Baker, Simon, Roth, Stefan, Scharstein, Daniel, Black, Michael J., Lewis, J.P., Szeliski, Richard·2007·2007 IEEE 11th International Conference on Computer Vision
DOI 10.1109/iccv.2007.4408903
Open this paper in CoChat — free account

Abstract

The quantitative evaluation of optical flow algorithms by Barron et al. led to significant advances in the performance of optical flow methods. The challenges for optical flow today go beyond the datasets and evaluation methods proposed in that paper and center on problems associated with nonrigid motion, real sensor noise, complex natural scenes, and motion discontinuities. Our goal is to establish a new set of benchmarks and evaluation methods for the next generation of optical flow algorithms. To that end, we contribute four types of data to test different aspects of optical flow algorithms: sequences with nonrigid motion where the ground-truth flow is determined by tracking hidden fluorescent texture; realistic synthetic sequences; high frame-rate video used to study interpolation error; and modified stereo sequences of static scenes. In addition to the average angular error used in Barron et al., we compute the absolute flow endpoint error, measures for frame interpolation error, improved statistics, and flow accuracy at motion boundaries and in textureless regions. We evaluate the performance of several well-known methods on this data to establish the current state of the art. Our database is freely available on the web together with scripts for scoring and publication of the results at http://vision.middlebury.edu/flow/.

Integrity signals

Registry

Crossref · 10.1109/iccv.2007.4408903

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

  • Prior to our evaluation (Baker et al. 2007), there were three major attempts to quantitatively evaluate optical flow algorithms, each proposing sequences with ground truth.

    “Prior to our evaluation (Baker et al. 2007), there were three major attempts to quantitatively evaluate optical flow algorithms, each proposing sequences with ground truth.”

    From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Baker et al. 2007

  • The best-performing algorithm in the preliminary study (Baker et al. 2007) was 2D-CLG (Bruhn et al. 2005), both in terms of average endpoint error and average angular error.

    “The best-performing algorithm (both in terms of average endpoint error and average angular error) in our preliminary study (Baker et al. 2007) was 2D-CLG (Bruhn et al. 2005).”

    From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Baker et al. 2007

  • The best results are a huge improvement over the algorithms in Baker et al. (2007) (Table 2).

    “The best results are a huge improvement over the algorithms in Baker et al. (2007) (Table 2).”

    From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Baker et al. 2007

  • Since the publication of the preliminary paper (Baker et al. 2007), a large number of authors have uploaded results to the online evaluation.

    “Since the publication of our preliminary paper (Baker et al. 2007), a large number of authors have uploaded results to our online evaluation.”

    From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Baker et al. 2007

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Baker, S., Roth, S., Scharstein, D., Black, M. J., Lewis, J. P., & Szeliski, R.
Affiliations
  • Microsoft (United States) (US)
  • Middlebury College (US)
  • Brown University (US)
ORCID
Venue
2007 IEEE 11th International Conference on Computer Vision
Publisher
IEEE
Published
2007
Pages
1-8
DOI
10.1109/iccv.2007.4408903
OpenAlex
W2034869517
Cited by
618
References
6
Citations by year
2026: 6 · 2025: 19 · 2024: 23 · 2023: 24 · 2022: 27 · 2021: 25 · 2020: 22 · 2019: 17 · 2018: 15 · 2017: 16 · 2016: 15 · 2015: 30 · 2014: 30 · 2013: 42 · 2012: 49
FWCI
46.73
Type
conference paper
Language
en
Open access
closed
Locations
  • IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
  • Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) (submittedVersion)
  • Fraunhofer-Publica (Fraunhofer-Gesellschaft) (submittedVersion)
  • MPG.PuRe (Max Planck Society) (submittedVersion)
Funders
National Science Foundation
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 › Signal Processing › Video Coding and Compression Technologies
Keywords
optical flow, benchmark dataset, evaluation methodology, non-rigid motion, motion discontinuities, high frame rate video, textureless regions, motion boundaries

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