AI Paper Atlas

Research map / Video / Video segmentation and tracking

Alignment-free HDR Deghosting with Semantics Consistent Transformer

Steven Tel, Zongwei Wu, Yulun Zhang, Barthélémy Heyrman, Cédric Demonceaux, Radu Timofte, Dominique Ginhac

ICCV 2023 · Video › Video segmentation and tracking · approach: Spike and neuromorphic deblurring · 69 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 G-SAB spatial attention block to baseline (ablation)SCTNet · Kalantari testmu-PSNR: 43.42 -> 44.04Improved
add S-CAB cross-frame channel attention on top of G-SAB (ablation)SCTNet · Kalantari testmu-PSNR: 44.04 -> 44.12Improved
add S-CAB on top of G-SAB (ablation)SCTNet · Kalantari testPSNR (linear): 41.89 -> 41.71Hurt
add skip connection from reference shallow feature (ablation)SCTNet · Kalantari testmu-PSNR / PSNR: 44.12 -> 44.49 (mu-PSNR); 41.71 -> 42.29 (PSNR)Improved
SCTNet versus HDR-TransformerSCTNet · Kalantari testmu-PSNR: 44.32 -> 44.49Improved
SCTNet versus HDR-Transformer on proposed datasetSCTNet · Proposed HDR datasetl-PSNR: 46.35 -> 47.51Improved
alignment-free attention design versus HDR-TransformerSCTNet · 1000x1500 inputGMACs: 981.81 -> 293.77Improved
SCTNet versus convolutional methods on runtimeSCTNet · Quadro P6000, 1000x1500Speed (s): 0.29 (HDR-GAN) vs 7.14Hurt

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