AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Removing Cost Volumes from Optical Flow Estimators

Simon Kiefhaber, Stefan Roth, Simone Schaub-Meyer

ICCV 2025 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 3 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
remove the cost volume from the start of training (never train with it) (ablation)ResNet-based RAFT-style estimator · SpringEPE: 0.68 -> 0.86Hurt
train with cost volume first, then cut it off (cut-off strategy) (ablation)ResNet-based estimator · SpringEPE: 0.86 -> 0.68Improved
fade out cost volume with dropout instead of hard cut-off (ablation)ReCoVEr training · SpringEPE: 0.68 vs 0.68No clear effect
delay cut-off point from TartanAir to FlyingThings stage (ablation)ReCoVEr-M training · SpringEPE: 0.86 -> 0.68Improved
delay cut-off further to the TSKH stage (ablation)ReCoVEr-M training · SpringEPE: 0.68 -> 0.71Hurt
replace ResNet-34 context network with ConvNeXt-t (ablation)ReCoVEr · SpringEPE: 0.68 -> 0.51Improved
replace ResNet-34 context network with MobileNetV3-L (ablation)ReCoVEr · SpringEPE: 0.68 -> 0.99Hurt
remove cost volume (ReCoVEr-L vs SEA-RAFT) at inferenceReCoVEr-L · Spring total EPEEPE: 0.54 -> 0.51Improved
remove cost volume at inferenceReCoVEr-L · Spring unmatched regionEPE: 7.25 -> 6.51Mixed
remove cost volume at inferenceReCoVEr-L · Out-of-domain Middlebury, MonkaaEPE: Monkaa Final 2.41 vs 2.46No clear effect
downsample 2x then upsample flowmost optical flow methods · Spring vs Sintel/MonkaaEPE: SEA-RAFT Spring 0.54 -> 0.41; Sintel Clean (0.43) -> (1.22)Mixed
increase refinement iterations beyond 4 (non-ResNet models) (ablation)ReCoVEr-S and ReCoVEr-L · Spring subsetEPENo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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