AI Paper Atlas

Research map / Video / Video segmentation and tracking

Spk2VidNet: A Hierarchical Recurrent Architecture for High-Fidelity Video Reconstruction from Long Spike-Camera Streams

Yuanlin Wang, Ruiqin Xiong, Jiyu Xie, Zhenkun Zhu, Zhaofei Yu, Xiaopeng Fan, Tiejun Huang

CVPR 2026 · Video › Video segmentation and tracking · approach: Real-world video super-resolution

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 MFCA module to baseline (2 layers) (ablation)Spk2VidNet baseline · REDS-LSSR (x4), full sequencePSNR: 28.39 -> 29.41Improved
add CMF module to baseline (2 layers) (ablation)Spk2VidNet baseline · REDS-LSSR (x4), full sequencePSNR: 28.39 -> 29.27Improved
combine MFCA and CMF (2 layers) (ablation)Spk2VidNet baseline · REDS-LSSR (x4), full sequencePSNR: 28.39 -> 29.79Improved
use independent alignment instead of MFCA (2 layers) (ablation)Spk2VidNet · REDS-LSSR (x4), full sequencePSNR: 29.41 -> 29.02Hurt
increase propagation layers from 1 to 2 (ablation)Spk2VidNet full · REDS-LSSR (x4), full sequencePSNR: 29.66 -> 29.79Improved
add second propagation layer to baseline without MFCA/CMF (ablation)Spk2VidNet baseline · REDS-LSSR (x4), full sequencePSNR: 28.37 -> 28.39No clear effect
add segment-wise training with state transfer (ablation)Spk2VidNet · REDS-LSSR (x4), full sequencePSNR: 29.58 -> 29.79Improved
add segment-wise training with state transfer (ablation)Spk2VidNet · REDS-LSSR (x4), full sequenceSSIM: 0.8377 -> 0.8432Improved
use Spk2VidNet instead of SCSRNetSCSR methods · Adobe240-LSSR (x4 SR)PSNR: 31.31 -> 32.36Improved
use Spk2VidNet instead of SCSRNetSCSR methods · REDS-LSSR (x8 SR)PSNR: 25.81 -> 26.20Improved
use Spk2VidNet instead of SCSRNet for runtimeSCSR methods · 180x320x461 input (x4)runtime (ms): 187 -> 43Improved

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