AI Paper Atlas

Research map / 3D vision / Depth and stereo

Consistency Guided Scene Flow Estimation

Yuhua Chen, Luc Van Gool, Cordelia Schmid, Cristian Sminchisescu

ECCV 2020 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 5 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 consistency guided refinement networkfeedforward module · KITTI 2015 scene flowSF outliers (%): 43.55 -> 35.40Improved
add consistency guided refinement networkfeedforward module · FlyingThings3D testflow EPE: 7.02 -> 5.98Improved
add self-supervised finetuning on KITTI after synthetic pretrainingCGSF · KITTI 2015 scene flowSF outliers (%): 35.40 -> 28.14Improved
add refinement without consistency inputs (prediction only) (ablation)feedforward · KITTI 2015 SF outliers ablation (trained on FlyingThings3D)SF outliers (%): 43.01 -> 42.43Improved
add stereo photometric consistency L_pd (ablation)refinement network · KITTI 2015 SF outliers ablation (trained on FlyingThings3D)SF outliers (%): 42.43 -> 39.80Improved
add flow photometric consistency L_pf (ablation)refinement network · KITTI 2015 SF outliers ablation (trained on FlyingThings3D)SF outliers (%): 42.43 -> 39.64Improved
add disparity-flow consistency L_df (ablation)refinement network · KITTI 2015 SF outliers ablation (trained on FlyingThings3D)SF outliers (%): 42.43 -> 39.59Improved
add L_df to L_pd and L_pf (ablation)refinement network · KITTI 2015 SF outliers ablation (trained on FlyingThings3D)SF outliers (%): 38.23 -> 35.40Improved
add loss as input to refinement network (ablation)refinement network · KITTI 2015 SF outliers ablation (trained on FlyingThings3D)SF outliers (%): 40.47 -> 35.40Improved
add gradient as input to refinement network (ablation)refinement network · KITTI 2015 SF outliers ablation (trained on FlyingThings3D)SF outliers (%): 36.31 -> 35.40Improved
learned refinement instead of output finetuning (ablation)refinement strategy · KITTI 2015 online refinement strategiesSF outliers (%): 39.95 -> 35.40Improved
learned refinement instead of parameter finetuning (ablation)refinement strategy · KITTI 2015 online refinement strategiesSF outliers (%): 35.49 -> 35.40No 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