AI Paper Atlas

Research map / Image generation / Super-resolution

ProSR: Semantic-Prototype-Guided Discrete Modeling for Physically Consistent SAR Super-Resolution

Byoungwoo Kim, Munchurl Kim

ECCV 2026 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 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 Detail-VQ instead of standard HR-VQ (ablation)ProSR AE · Stage 1 AE reconstructionPSNR: 16.5177 -> 18.1018Improved
use Detail-VQ instead of Dual-VQ (ablation)ProSR AE · Stage 1 AE reconstructionSSIM: 0.3296 -> 0.3799Improved
increase codebook size from 512 to 1024 (ablation)ProSR AE · Stage 1 AE reconstructionPSNR: 17.9659 -> 18.1018Improved
increase codebook size from 1024 to 2048 (ablation)ProSR AE · Stage 1 AE reconstructionPSNR: 18.1018 -> 18.0894No clear effect
add PMGA instead of vanilla cross-attention (ablation)ProSR · SAR ISR x4 benchmarkFID: 25.39 -> 23.70Improved
add PMGA instead of vanilla cross-attention (ablation)ProSR · SAR ISR x4 benchmarkDens: 0.9404 -> 0.9741Improved
add PMGA instead of vanilla cross-attention (ablation)ProSR · SAR ISR x4 benchmarkIW-SSIM: 0.4186 -> 0.4206Improved
use discrete token prediction instead of continuous DiT-style modeling (ablation)ProSR · SAR ISR x4 benchmarkFID: 40.43 -> 23.70Improved
add stochastic LR-patch training in the AE (p=0.25 vs p=0) (ablation)ProSR AE · Stage 1 AE reconstructionSSIM: 0.1024 -> 0.3799Improved
raise stochastic training probability from 0.25 to 0.5 (ablation)ProSR AE · Stage 1 AE reconstructionPSNR/LPIPS: PSNR 18.1018 -> 18.1822, LPIPS 0.2044 -> 0.2159Mixed
use ProSR outputs instead of strongest baseline UPSR for ATRProSR · MSTAR ATR transferaccuracy (%): 84.18 -> 88.39Improved
use prototype token count K=3 instead of K=2 or K>=4 (ablation)SPMG · semantic prototype mapssemantic map qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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