AI Paper Atlas

Research map / 3D vision / Depth and stereo

RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation

Zhexiong Wan, Yuxin Mao, Jing Zhang, Yuchao Dai

ICCV 2023 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 33 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 event data to the framework (ablation)RPEFlow · FlyingThings3D valEPE2D: 2.067 -> 1.402Improved
add event feature to CamLiFlow decoder (ablation)CamLiFlow · FlyingThings3D valEPE2D: 2.20 -> 1.56Improved
add event feature to RAFT decoder (ablation)RAFT · FlyingThings3D valEPE2D: 3.12 -> 2.49Improved
replace concat fusion with attention fusion (no event) (ablation)RPEFlow · FlyingThings3D valEPE2D: 2.200 -> 2.133Improved
replace concat fusion with attention fusion (with event) (ablation)RPEFlow · FlyingThings3D valEPE2D: 1.519 -> 1.494Improved
add mutual information regularization (no event) (ablation)RPEFlow · FlyingThings3D valEPE2D: 2.133 -> 2.067Improved
add mutual information regularization (with event) (ablation)RPEFlow · FlyingThings3D valEPE2D: 1.494 -> 1.402Improved
add event into the concat fusion (ablation)RPEFlow concat variant · FlyingThings3D valEPE2D: 1.561 -> 1.519Improved
train 2D and 3D branches jointly instead of 2D only (ablation)RPEFlow · FlyingThings3D valEPE2D: 1.937 -> 1.402Improved
train 2D and 3D branches jointly instead of 3D only (ablation)RPEFlow · FlyingThings3D valEPE3D (Full): 0.078 -> 0.042Improved
add event to RGB+PC input with CamLiFlow, ACC1pxCamLiFlow · FlyingThings3D valACC1px: 84.6% -> 84.4%No clear effect

Later papers that compared with this method

1 later accepted paper reports RPEFlow as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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