AI Paper Atlas

Research map / Video / Video segmentation and tracking

Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data

Joel Janai, Fatma Guney, Jonas Wulff, Michael J. Black, Andreas Geiger

CVPR 2017 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 86 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use the full dense tracking model rather than Epic Flow at 24fpsSlow Flow · MPI Sintel, all regionsEPE: 5.53 -> 2.58Improved
use the full dense tracking model rather than Epic Flow at 24fpsSlow Flow · MPI Sintel, occluded regionsEPE: 16.54 -> 9.45Improved
use the full dense tracking model rather than Epic Flow at 24fpsSlow Flow · MPI Sintel, visible regionsEPE: 2.45 -> 0.87Improved
add dense tracking with temporal and occlusion reasoning instead of accumulating Flowlets at 144fps (ablation)Slow Flow · MPI Sintel, all regionsEPE: 4.03 -> 2.58Improved
add dense tracking with temporal and occlusion reasoning instead of accumulating Flowlets at 144fps (ablation)Slow Flow · MPI Sintel, occluded regionsEPE: 15.24 -> 9.45Improved
accumulate multi-frame Flowlets at 1008fps rather than choosing a coarser frame rate (ablation)Slow Flow · MPI Sintel, all regionsEPE: 4.03 -> 5.38Hurt
accumulate multi-frame Flowlets at 1008fps rather than 144fps (ablation)Slow Flow · MPI Sintel, visible regionsEPE: 0.78 -> 1.35Hurt
accumulate multi-frame Flowlets at 1008fps rather than 144fps (ablation)Slow Flow · MPI Sintel, motion-boundary edgesEPE: 11.78 -> 2.60Improved
estimate occlusions with the proposed method rather than a forward/backward EpicFlow checkSlow Flow · MPI Sintelocclusion Jaccard Index: 62.86% -> 70.09%Improved
use Slow Flow rather than Epic FlowOptical flow on real-world static scenes · Flow Magnitude 100EPE: 1.54 -> 1.47No clear effect
use Slow Flow rather than Epic FlowOptical flow on real-world static scenes · Flow Magnitude 300EPE: 25.11 -> 5.13Improved
use realistic motion-blurred inputsmatching-based optical flow methods · Real-world benchmark, varying motion magnitudesEPEHurt

Later papers that compared with this method

1 later accepted paper reports SlowFlow as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy