AI Paper Atlas

Research map / 3D vision / Depth and stereo

Flow-Anything: Learning Real-World Optical Flow Estimation From Large-Scale Single-View Images

Yingping Liang, Ying Fu, Yutao Hu, Wenqi Shao, Jiaming Liu, Debing Zhang

TPAMI 2025 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 18 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
add dynamic objects to generated data (ablation)Flow-Anything RAFT · KITTI 15EPE: 2.47 -> 1.80Improved
add dynamic objects to generated data (ablation)Flow-Anything RAFT · KITTI 12EPE: 1.19 -> 1.29Hurt
add depth-aware (object-aware) inpainting (ablation)Flow-Anything RAFT · KITTI 15EPE: 1.80 -> 1.85No clear effect
add depth-aware (object-aware) inpainting (ablation)Flow-Anything RAFT · KITTI 12EPE: 1.29 -> 1.24Improved
add multiple moving objects (ablation)Flow-Anything RAFT · KITTI 15EPE: 1.85 -> 1.79Improved
use Flow-Anything instead of MPI-Flow for data generationRAFT · KITTI 15 (COCO images)Fl: 10.66 -> 10.32Improved
train on FA-Flow Dataset instead of C+T (+K+S+H)SEA-RAFT · KITTI 15 train zero-shotEPE: 4.29 -> 1.64Improved
train on FA-Flow Dataset instead of synthetic C+T+VK2SEA-RAFT · KITTI 15EPE: 2.27 -> 1.64Improved
train on FA-Flow Dataset instead of C+T (+K+S+H)SEA-RAFT · Sintel FinalEPE: 4.04 -> 2.22Improved
train on FA-Flow Dataset instead of C+T (+K+S+H)FlowFormer++ · KITTI 15 train zero-shotEPE: 3.93 -> 1.89Improved
increase generated COCO data from 20K to 120K (ablation)RAFT from scratch · KITTI 15EPE: 3.68 -> 3.41Improved
use FA-Flow data instead of C+T when training from scratchRAFT · KITTI 15EPE: 5.00 -> 3.41Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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