AI Paper Atlas

Research map / Video / Video segmentation and tracking

Unsupervised Learning of Multi-Frame Optical Flow with Occlusions

Joel Janai, Fatma Guney, Anurag Ranjan, Michael Black, Andreas Geiger

ECCV 2018 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 203 citations (OpenAlex)

Read the paperCheck 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
extend two-frame PWC-Net to three frames (ablation)PWC-Net · RoamingImages testEPE (all): 14.14 -> 10.11Improved
add occlusion reasoning to the multi-frame model (ablation)Multi · RoamingImages testEPE (all): 10.11 -> 6.93Improved
add occlusion reasoning to the multi-frame model (ablation)Multi · RoamingImages testEPE (occluded): 18.22 -> 8.55Improved
add hard constant velocity constraint (ablation)Ours-None · RoamingImages testEPE (occluded): 16.26 -> 8.55Improved
add hard constant velocity constraint (ablation)Ours-None · RoamingImages testEPE (all): 8.37 -> 6.93Improved
add soft constant velocity constraint (ablation)Ours-None · RoamingImages testEPE (all): 8.37 -> 8.17No clear effect
fine-tune with hard constraint on MPI Sintel (ablation)Ours-Hard · MPI Sintel Clean trainEPE (all): 5.38 -> 6.05Hurt
use soft instead of no temporal constraint in fine-tuning (ablation)Ours-None-ft · MPI Sintel Clean trainEPE (all): 4.74 -> 3.89Improved
use soft instead of no temporal constraint in fine-tuning (ablation)Ours-None-ft · KITTI 2015 trainEPE (all): 6.65 -> 6.59No clear effect
use soft instead of no temporal constraint in fine-tuning (ablation)Ours-None-ft · MPI Sintel Final trainEPE (occluded): 12.66 -> 12.87Mixed
pretrain UnFlow-CSS on RoamingImages instead of its default data (control for dataset)UnFlow-CSS · KITTI 2015 trainEPE (all): 8.10 -> 19.26Hurt
use the multi-frame model pretrained only (no fine-tuning) vs prior pretrained bestOurs-Hard · MPI Sintel Final trainEPE (all): 6.34 -> 6.01Improved

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