AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation

Zhaoyang Lv, Kihwan Kim, Alejandro Troccoli, Deqing Sun, James M. Rehg, Jan Kautz

ECCV 2018 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 86 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 RTN-learned rigidity to pose refinement (ablation)Refine only · SINTEL test split clean, no finetuningprojected scene flow EPE: 8.47 -> 5.10Improved
use RTN rigidity instead of semantic rigidity (ablation)Refine pipeline · SINTEL test split clean, no finetuningprojected scene flow EPE: 6.42 -> 5.10Improved
use RTN rigidity instead of semantic rigidity (ablation)Refine pipeline · SINTEL test split final, no finetuningprojected scene flow EPE: 12.81 -> 6.29Improved
add joint pose learning to RTN (ablation)RTN + Refine · SINTEL test split clean, no finetuningprojected scene flow EPE: 7.09 -> 5.10Improved
add joint pose learning to RTN (ablation)RTN + Refine · SINTEL test split final, no finetuningprojected scene flow EPE: 7.14 -> 6.29Improved
train RTN on REFRESH instead of Things3D (ablation)RTN + Refine · SINTEL test split final, no finetuningprojected scene flow EPE: 11.88 -> 6.29Improved
train RTN on REFRESH instead of Things3D (ablation)RTN · SINTEL clean valrigidity mean IOU: 0.283 -> 0.542Improved
use RTN rigidity instead of semantic rigidity (ablation)RTN trained on REFRESH · SINTEL clean valrigidity mean IOU: 0.392 -> 0.542Improved
use RTN rigidity instead of semantic rigidity (ablation)RTN trained on REFRESH · SINTEL final valrigidity mean IOU: 0.446 -> 0.627Improved
use RTN rigidity instead of semantic rigidity (ablation)RTN trained on REFRESH · REFRESH valrigidity mean IOU: 0.934 -> 0.956Improved
finetune RTN on SINTEL (ablation)RTN + Refine · SINTEL test split clean, no finetuningprojected scene flow EPE: 5.10 -> 5.03No clear effect
finetune RTN on SINTEL (ablation)RTN + Refine · SINTEL test split final, no finetuningprojected scene flow EPE: 6.29 -> 6.12No clear effect

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