AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

From Local to Global: A Progressive Reconstruction Network for Diffractive Snapshot Spectral Imaging

Zhengyue Zhuge, Shiqi Chen, Chi Zhang, Jiahui Xu, Tianchen Qiu, Dingchuan Yu, Yueting Chen

ECCV 2026 · Architectures and efficiency › Attention and transformers · approach: Efficient image transformers · 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
use local-to-global two-stage design instead of single-stage global (ablation)LGSRNet · ICVL+VNIRSR (combined)PSNR (dB): 39.35 -> 39.76Improved
use local-to-global two-stage design instead of single-stage global (ablation)LGSRNet · ICVL+VNIRSR (combined)GFLOPs: 118.07 -> 102.34Improved
arrange local and global modules in parallel instead of local-to-global (ablation)LGSRNet · ICVL+VNIRSR (combined)PSNR (dB): 39.76 -> 38.34Hurt
arrange local and global modules alternately instead of local-to-global (ablation)LGSRNet · ICVL+VNIRSR (combined)PSNR (dB): 39.76 -> 38.92Hurt
replace local-first stage with a second global stage (ablation)LGSRNet · ICVL+VNIRSR (combined)PSNR (dB): 39.76 -> 39.65Hurt
add SGCA channel attention instead of SCA (no FF) (ablation)LGSRNet w/o FF · ICVL+VNIRSR (combined)PSNR (dB): 38.63 -> 39.00Improved
add SCA channel attention without feature fusion (ablation)LGSRNet w/o FF · ICVL+VNIRSR (combined)PSNR (dB): 38.64 -> 38.63Hurt
add EAGF feature fusion (no channel attention) (ablation)LGSRNet w/o CA · ICVL+VNIRSR (combined)PSNR (dB): 38.64 -> 39.14Improved
combine SGCA and EAGF versus neither (ablation)LGSRNet · ICVL+VNIRSR (combined)PSNR (dB): 38.64 -> 39.76Improved
use EAGF instead of CSFF fusion (ablation)LGSRNet · ICVL+VNIRSR (combined)PSNR (dB): 39.59 -> 39.76Improved
use ECSS sample selection instead of gradient-based selection (ablation)LGSRNet · ICVL+VNIRSR (combined)PSNR (dB): 39.44 -> 39.50Improved
use ECSS sample selection instead of no selection (ablation)LGSRNet · ICVL+VNIRSR (combined)PSNR (dB): 39.26 -> 39.50Improved

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