AI Paper Atlas

Research map / Image generation / Super-resolution

Towards Robust Full Low-bit Quantization of Super Resolution Networks

Denis S. Makhov, Irina Zhelavskaya, Ruslan Ostapets, Dehua Song, Kirill Solodskikh

ECCV 2024 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 2 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
wrap quantized SR network with finite-difference operator and regularized PDE solverEDSR x2 W4A4 · DIV2KPSNR (dB): 30.23 -> 33.98Improved
wrap quantized SR network with operator and PDE solverRFDN x2 W4A4 · DIV2KPSNR (dB): 30.09 -> 33.76Improved
use regularized PDE solver instead of inverse filtering (ablation)SRCNN x3 · Set5PSNR (dB): 32.27 -> 32.65Improved
use regularized PDE solver instead of inverse filtering (ablation)SRCNN x3 · Urban100LPIPS: 0.240 -> 0.213Improved
apply method at lower bitwidths for EDSR x2 (ablation)Ours vs LSQ+ · EDSR x2, 2-bitPSNRImproved
compare with DAQ and CADYQ for full 4-bitEDSR x2 Urban100 · Urban100PSNR (dB): 30.84 -> 31.14 over CADYQImproved
add differential operator and PDE solver to quantized networkEDSR x2 W4A4 · BitOpsBitOps (G): 5.63 -> 6.41Hurt
add method to SRCNN x2 W4A4 versus FPSRCNN x2 · Set5PSNR (dB): 34.23 -> 37.18Improved

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