AI Paper Atlas

Research map / Video / Video segmentation and tracking

SNN-Driven Event-Based Flow and Rotation Estimation with SO(3) Refinement

Ruimin Sun, Haoran Xu, De Ma

AAAI 2026 · Video › Video segmentation and tracking · approach: Spike and neuromorphic deblurring · 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
carry LIF membrane potential across 10ms segments (ablation)SNN optical flow model · DSEC-FlowEPE: 1.97 -> 0.87Improved
use Spike GRU instead of ConvGRU (ablation)SNN optical flow model · DSEC-FlowEPE: 0.85 -> 0.87Hurt
use Spike GRU instead of ConvGRUSNN optical flow model · energy per inferenceFLOPs per GRU (G): 1.26G -> 0.84GImproved
convert TIDNet to fully spiking SNNTIDNet · DSEC-Flowenergy (pJ): 135.30 -> 3.55Improved
add SO(3) gradient refinement (ablation)SNN rotation estimation · ECRot Main Buildingmean rotation error (rad): 0.386 -> 0.110Improved
increase extracted keypoints from 16 to 24 or 32 (ablation)SNN rotation estimation · ECRot Main Buildingmean rotation error (rad): 0.386 -> 0.422No 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