AI Paper Atlas

Research map / 3D vision / Depth and stereo

x^2-Fusion: Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Space

Ruishan Guo, Ciyu Ruan, Haoyang Wang, Zihang Gong, Jingao Xu, Xinlei Chen

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 Event Edge Space (ablation)x^2-Fusion · DSEC valEPE 2D: 0.491 -> 0.322Improved
add Event Edge Space (ablation)x^2-Fusion · DSEC valEPE 3D: 0.146 -> 0.094Improved
add edge-anchored symmetric regularization (ablation)x^2-Fusion · DSEC valEPE 2D: 0.393 -> 0.322Improved
add edge-anchored symmetric regularization (ablation)x^2-Fusion · DSEC valEPE 3D: 0.119 -> 0.094Improved
pretrain the event edge encoder (ablation)x^2-Fusion · DSEC valEPE 2D: 0.378 -> 0.322Improved
pretrain the event edge encoder (ablation)x^2-Fusion · DSEC valEPE 3D: 0.114 -> 0.094Improved
joint 2D and 3D estimation instead of independent (ablation)x^2-Fusion · DSEC valEPE 2D: 0.404 -> 0.386Improved
joint 2D and 3D estimation instead of independent (ablation)x^2-Fusion · DSEC valEPE 3D: 0.119 -> 0.113Improved
add cross-dimension contrastive learning (CCL) to joint training (ablation)x^2-Fusion · DSEC valEPE 2D: 0.386 -> 0.325Improved
add cross-dimension contrastive learning (CCL) to joint training (ablation)x^2-Fusion · DSEC valEPE 3D: 0.113 -> 0.103Improved
use x^2-Fusion instead of RPEFlow under drifting LiDARx^2-Fusion · DSEC-PC driftingEPE 2D: 1.051 -> 0.409Improved
use x^2-Fusion instead of RPEFlow under under-exposurex^2-Fusion · EKubric-Img under-exposureEPE 2D: 3.663 -> 1.143Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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