AI Paper Atlas

Research map / Video / Video segmentation and tracking

MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation

Vladislav Bargatin, Egor Chistov, Alexander Yakovenko, Dmitriy Vatolin

ICCV 2025 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 8 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
train on 2x upsampled full frames instead of native-resolution data (ablation)MEMFOF · Spring trainEPE: 0.430 -> 0.341Improved
use full upsampled frames instead of crops (ablation)MEMFOF · Spring trainEPE: 0.378 -> 0.341Improved
predict flow at full resolution instead of half-scale inference (native training) (ablation)MEMFOF · Spring trainEPE: 0.402 -> 0.430Mixed
bidirectional instead of unidirectional flow (ablation)MEMFOF · Spring trainEPE: 0.400 -> 0.341Improved
correlation volume at 1/16 instead of 1/24 resolution (ablation)MEMFOF (3 frames) · Spring train1px outlier rate: 3.480 -> 3.061Improved
increase update dimension Dc from 128 to 512 (ablation)MEMFOF (3 frames) · Spring train1px outlier rate: 3.560 -> 3.061Improved
add GMA module (ablation)MEMFOF (3 frames) · Spring train1px outlier rate: 3.151 -> 3.061Improved
add GMA module (ablation)MEMFOF (3 frames) · Spring trainEPE: 0.332 -> 0.341Hurt
use 3 frames instead of 2 frames (ablation)MEMFOF (1/16) · Spring train1px outlier rate: 3.375 -> 3.061Improved
use 5 frames instead of 3 frames (ablation)MEMFOF (1/24) · Spring train1px outlier rate: 3.480 -> 3.809Hurt
add inference-time optimizations (late upsampling, feature/correlation reuse, fast correlation) (ablation)MEMFOF (3 frames) · Inference timetime (ms): 611 -> 472Improved
increase iterations N from 1 to 8 (ablation)MEMFOF · Spring train1px outlier rate: 3.752 -> 3.061Improved

Later papers that compared with this method

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

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