AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation

Qingwen Zhang, Chenhan Jiang, Xiaomeng Zhu, Yunqi Miao, Yushan Zhang, Olov Andersson, Patric Jensfelt

CVPR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 2 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
use 5 input frames instead of 2 (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.353 -> 0.265Improved
use 5 input frames instead of 8 (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.300 -> 0.265Improved
add static loss to geometric loss (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.386 -> 0.458Hurt
add dynamic cluster loss to geometric and static losses (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.458 -> 0.265Improved
add cluster-level term to point-level loss (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.351 -> 0.265Improved
add point-level term to cluster-level loss (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.356 -> 0.265Improved
add external geometric candidates to internal predictions (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.455 -> 0.265Improved
add internal candidate to external candidates (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.321 -> 0.265Improved
add directional consistency agreement matrix M (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.349 -> 0.265Improved
add reliability weights w (ablation)TeFlow · Argoverse 2 valthree-way EPE mean: 5.70 -> 4.43Improved
add flow aggregation of consistent candidates (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.289 -> 0.265Improved
use DeltaFlow backbone instead of Flow4D (ablation)TeFlow · Argoverse 2 valdynamic bucket-normalized EPE: 0.330 -> 0.265Improved

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