AI Paper Atlas

Research map / Video / Video segmentation and tracking

ARFlow: Auto-regressive Optical Flow Estimation for Arbitrary-Length Videos via Progressive Next-Frame Forecasting

Jiuming Liu, Mengmeng Liu, Siting Zhu, Yunpeng Zhang, Jiangtao Li, Michael Ying Yang, Francesco Nex, Hao Cheng, Hesheng Wang

ICLR 2026 · Video › Video segmentation and tracking · approach: Learned optical flow estimation

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
add Auto-regressive Flow Initialization (AFI) (ablation)ARFlow · KITTI-15 train (C+T)EPE: 3.05 -> 2.86Improved
add AFI (ablation)ARFlow · Sintel train (C+T)EPE Clean/Final: 0.95/2.15 -> 0.88/2.07Improved
add Auto-regressive Multi-stride Flow Refinement (AMFR) (ablation)ARFlow · KITTI-15 train (C+T)EPE: 3.00 -> 2.86Improved
use strides 1+2+4 instead of single stride 4 (ablation)AMFR · KITTI-15 train (C+T)EPE: 3.00 -> 2.86Improved
use strides 1+2+4 instead of single stride 1 (ablation)AMFR · KITTI-15 train (C+T)F1-all: 9.52 -> 9.21Improved
increase memory length T from 4 to 6 (ablation)ARFlow · KITTI-15 train (C+T)EPE: 2.96 -> 2.86Improved
increase memory length T from 6 to 8 (ablation)ARFlow · KITTI-15 train (C+T)EPE: 2.86 -> 2.86No clear effect
increase GRU iterations K from 4 to 6 (ablation)ARFlow · KITTI-15 train (C+T)F1-all: 9.89 -> 9.21Improved
increase GRU iterations K from 6 to 8 (ablation)ARFlow · KITTI-15 train (C+T)F1-all: 9.21 -> 9.23No clear effect
store memory flows at 1/16 instead of full resolution (ablation)ARFlow · KITTI-15 train (C+T)F1-all: 9.27 -> 9.21No clear effect
replace temporal transformer with pre-trained WAN2.2 (5B) (ablation)ARFlow · KITTI-15 train (C+T)F1-all: 9.21 -> 9.56Hurt
integrate ARFlow into SEA-RAFT(L)SEA-RAFT(L) · Sintel train Final (C+T)EPE: 4.11 -> 3.72Improved

Later papers that compared with this method

1 later accepted paper reports ARFlow 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 3 of 3 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