AI Paper Atlas

Research map / 3D vision / Depth and stereo

Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation

Eddy Ilg, Tonmoy Saikia, Margret Keuper, Thomas Brox

ECCV 2018 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 194 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
provide ground-truth forward flow as input to occlusion network (ablation)FlowNetS occlusion estimation · FlyingThings3DF-measure: 0.790 -> 0.932Improved
provide ground-truth forward flow as input to occlusion network (ablation)FlowNetS occlusion estimation · Sintel cleanF-measure: 0.545 -> 0.653Improved
add warped and flipped backward flow input (ablation)FlowNetS occlusion estimation · FlyingThings3DF-measure: 0.932 -> 0.943Improved
add raw backward flow input (ablation)FlowNetS occlusion estimation · FlyingThings3DF-measure: 0.932 -> 0.930No clear effect
estimate occlusions jointly with flow (ablation)FlowNetC · Sintel train cleanEPE: 3.21 -> 3.20No clear effect
add forward/backward flow estimation (FlowNetC-Bi) (ablation)FlowNetC joint flow and occlusion · Sintel train cleanEPE: 3.20 -> 3.26Hurt
add occlusion estimation to refinement stack (ablation)FlowNet2-CS · Sintel train cleanEPE: 2.28 -> 2.25No clear effect
add backward direction estimation to stack (ablation)FlowNet2-CS with occlusions · Sintel train cleanEPE: 2.25 -> 2.77Hurt
add mutual warping of fwd/bwd flows (ablation)FlowNet2-CS with occlusions · Sintel train cleanEPE: 2.25 -> 2.25No clear effect
use own occlusions in motion segmentation with FlowNet2 flowKeuper motion segmentation · FBMS-59 test (8px)F-measure: 76.71% -> 77.14%Improved
replace FlowNet2 flow and occlusions with oursKeuper motion segmentation · FBMS-59 test (8px)F-measure: 76.71% -> 80.45%Improved
move correlation layer from level 2 to level 3 (ablation)DispNetC · Sintel train clean disparityEPE: 5.62 -> 3.19Improved

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