AI Paper Atlas

Research map / Video / Video segmentation and tracking

SplatFlow: Learning Multi-frame Optical Flow via Splatting

Bo Wang, Yifan Zhang, Jian Li, Yang Yu, Zhenping Sun, Li Liu, Dewen Hu

IJCV 2024 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 19 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 forward-warp splatting alignment instead of backward warp (ablation)SplatFlow-GMA · Things val CleanEPE: 3.23 -> 3.02Improved
add forward-warp splatting alignment instead of backward flow (ablation)SplatFlow-GMA · KITTI trainEPE: 4.30 -> 3.70Improved
make splatting differentiable instead of gradient-disabled (ablation)SplatFlow-GMA · Things val CleanEPE: 3.25 -> 3.02Improved
use sub-pixel splatting instead of nearest filling (ablation)SplatFlow-GMA · Things val CleanEPE: 4.11 -> 3.25Improved
average splatting instead of softmax splatting (ablation)SplatFlow-GMA · KITTI trainEPE: 3.92 -> 3.70Improved
average splatting instead of softmax splatting (ablation)SplatFlow-GMA · Things val CleanEPE: 2.97 -> 3.02Hurt
Final-to-All embedding instead of One-to-One (ablation)SplatFlow-GMA · Things val FinalEPE: 3.43 -> 3.23Improved
Final-to-All embedding instead of Final-to-Final (ablation)SplatFlow-GMA · Things val FinalEPE: 4.09 -> 3.23Improved
add multi-frame SplatFlow to GMAGMA · Sintel test FinalEPE: 2.47 -> 2.07Improved
add multi-frame SplatFlow to RAFTRAFT · Things val CleanEPE: 5.24 -> 3.43Improved
add multi-frame SplatFlow to RAFTRAFT · Sintel train FinalEPE: 2.70 -> 2.84Hurt
add WarmStart to GMAGMA · Things val CleanEPE: 4.98 -> 5.16Hurt

Later papers that compared with this method

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

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