AI Paper Atlas

Research map / Video / Video segmentation and tracking

EfficientSCI: Densely Connected Network With Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging

Lishun Wang, Miao Cao, Xin Yuan

CVPR 2023 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 39 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 dense connections within ResDNet at GN 4 (ablation)EfficientSCI · Six grayscale benchmark datasetsPSNR: 35.02 -> 36.48Improved
Replace SCB with Swin Transformer (ablation)EfficientSCI CFormer · Six grayscale benchmark datasetsPSNR: 35.51 -> 34.99Hurt
Replace SCB and TSAB with two stacked 3D convolutions (ablation)EfficientSCI CFormer · Six grayscale benchmark datasetsPSNR: 35.51 -> 34.93Hurt
Increase the number of channels and blocks (ablation)EfficientSCI · Six grayscale benchmark datasetsPSNR: 34.22 -> 35.51 -> 36.48 -> 36.92Improved
Remove regularization layers (ablation)EfficientSCI CFormer · Video SCI reconstructionreconstruction qualityNo 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