AI Paper Atlas

Research map / Image generation / Super-resolution

SPR$^2$Q: Static Priority-based Rectifier Routing Quantization for Image Super-Resolution

Jingwei Xin, Wenhao Li, Nannan Wang, Jie Li, Xinbo Gao

ICLR 2026 · Image generation › Super-resolution · approach: Perceptual and real-world SR

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 pre-quantization fused low-rank rectifier (PQFR) (ablation)MambaIRv2-light 4-bit · Set5 x2 / Urban100 x2PSNR: Set5 37.20 -> 37.44; Urban100 30.69 -> 31.25Improved
add rectifier group training (RGT) (ablation)SPR2Q with PQFR · Set5 x2PSNR: 37.44 -> 37.60Improved
add rectifier group training (RGT) (ablation)SPR2Q with PQFR · Urban100 x2PSNR: 31.25 -> 31.24No clear effect
add offline static routing calibration (OSRC) (ablation)SPR2Q with PQFR and RGT · Set5 x2 / Urban100 x2PSNR: Set5 37.60 -> 37.72; Urban100 31.24 -> 31.53Improved
increase rectifier rank from 8 to 16 (ablation)SPR2Q · Set5 x2PSNR: 37.72 -> 37.74No clear effect
increase rectifier rank from 2 to 8 (ablation)SPR2Q · Set5 x2PSNR: 37.63 -> 37.72Improved
increase rectifier group size from 2 to 4 (ablation)SPR2Q · Set5 x2PSNR: 37.50 -> 37.72Improved
increase rectifier group size from 4 to 8 (ablation)SPR2Q · Set5 x2PSNR: 37.72 -> 37.82Improved
use SPR2Q instead of Mamba PTQ baselines at 4-bitPTQ4VM/Quamba/MambaQuant · Urban100 x2PSNR: 30.54 -> 31.53Improved
use SPR2Q instead of Mamba PTQ baselines at 2-bitQuamba · Set5 x2PSNR: 34.66 -> 35.97Improved
apply SPR2Q instead of ViT PTQ methods to SwinIR-light at 2-bitAPHQ-ViT · Set5 x2PSNR: 36.14 -> 37.28Improved
quantize from 2-bit to 1-bit (ablation)SPR2Q · Set5 x2PSNR: 35.97 -> 34.82Hurt

Later papers that compared with this method

1 later accepted paper reports SPR2Q as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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