AI Paper Atlas

Research map / 3D vision / Depth and stereo

ReFlow: Self-correction Motion Learning for Dynamic Scene Reconstruction

Yanzhe Liang, Ruijie Zhu, Hanzhi Chang, Zhuoyuan Li, Jiahao Lu, Tianzhu Zhang

CVPR 2026 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 0 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 ReFlow (initialization, separation, self-correction flow matching) to 4DGS4DGS · NVIDIA Monocular meanPSNR: 25.81 -> 28.20Improved
use ReFlow instead of MoDec-GSMoDec-GS · NVIDIA Monocular per-scene SSIMSSIM: Balloon2 0.909 -> 0.908; Jumping 0.858 -> 0.855; mean 0.879 -> 0.903Mixed
add ReFlow to 4DGS4DGS · HyperNeRFPSNR: 25.16 -> 26.15Improved
add self-correction flow matching to baseline (ablation)4DGS baseline · NVIDIA MonocularPSNR: 25.81 -> 26.45Improved
add raw unaligned point cloud initialization (ablation)4DGS baseline · NVIDIA MonocularPSNR: 25.81 -> 24.50Hurt
add hierarchical aligned canonical space initialization (ablation)4DGS baseline · NVIDIA MonocularPSNR: 25.81 -> 26.60Improved
add static-dynamic separation (ablation)aligned init · NVIDIA MonocularPSNR: 26.60 -> 27.00Improved
add Full Flow Matching (ablation)init + separation · NVIDIA MonocularPSNR: 27.00 -> 27.85Improved
add Camera Flow Matching (ablation)init + separation + Full FM · NVIDIA MonocularPSNR: 27.85 -> 28.20Improved

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