AI Paper Atlas

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

RAFT-MSF: Self-Supervised Monocular Scene Flow Using Recurrent Optimizer

Bayram Bayramli, Junhwa Hur, Hongtao Lu

IJCV 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 12 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 gradient detaching on the convex upsampling mask head (ablation)RAFT-MSF · KITTI 2015 Scene Flow TrainingSF-all (%): 38.37 -> 37.37Improved
add disparity initialization with two conv layers on top of gradient detach (ablation)RAFT-MSF · KITTI 2015 Scene Flow TrainingSF-all (%): 37.37 -> 35.62Improved
add gradient detach and disparity init together to RAFT baseline (ablation)RAFT-MSF · KITTI 2015 Scene Flow TrainingD1-all (%): 26.95 -> 24.04Improved
initialize disparity with 1 conv layer instead of zeros (ablation)RAFT-MSF · KITTI 2015 Scene Flow TrainingSF-all (%): 37.37 -> 36.15Improved
use 2 conv layers instead of 1 for disparity initialization (ablation)RAFT-MSF · KITTI 2015 Scene Flow TrainingSF-all (%): 36.15 -> 35.62Improved
initialize disparity with one or half of maximum disparity instead of zeros (ablation)RAFT-MSF · KITTI 2015 Scene Flow Trainingtraining convergenceHurt
use convex upsampling without gradient detaching in self-supervised setup (ablation)RAFT-MSF · KITTI 2015 Scene Flow TrainingartifactsHurt
replace prior two-view method with RAFT-based baselineRAFT baseline · KITTI 2015 Scene Flow TrainingSF-all (%): 47.05 -> 38.27Improved
RAFT-MSF vs prior multi-view method using only two viewsRAFT-MSF · KITTI 2015 Scene Flow TrainingSF-all (%): 39.82 -> 30.97Improved
fine-tune with 200 annotated pairsRAFT-MSF · KITTI 2015 Scene Flow TestSF-all (%): 34.98 -> 22.50Improved
fine-tune with 200 annotated pairsRAFT-MSF · KITTI 2015 Scene Flow TestFl-all (%): 18.37 -> 8.80Improved
RAFT-MSF vs prior depth methods on Eigen splitRAFT-MSF · Eigen split depthAbs Rel: 0.093No 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