AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Image Quality Assessment: Unifying Structure and Texture Similarity

Keyan Ding, Kede Ma, Shiqi Wang, Eero P. Simoncelli

TPAMI 2020 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 1,150 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
replace max pooling with l2 pooling (ablation)LPIPS · SynTEXSRCC: 0.589 -> 0.592Improved
add input image as zeroth stage (ablation)LPIPS with l2 pooling · LIVESRCC: 0.938 -> 0.935No clear effect
replace Euclidean distance with global SSIM-like measures (ablation)LPIPS + input image · TQDSRCC: 0.409 -> 0.795Improved
replace Euclidean distance with global SSIM-like measures (ablation)LPIPS + input image · LIVE_AugSRCC: 0.789 -> 0.881Improved
use local 11x11 SSIM instead of global SSIM (ablation)LPIPS + input image · SynTEXSRCC: 0.877 -> 0.744Hurt
local SSIM instead of Euclidean distance (ablation)LPIPS + input image · TQDSRCC: 0.409 -> 0.667Improved
add E2 texture-invariance training term (ablation)global SSIM model · TQDSRCC: 0.795 -> 0.910Improved
add E2 texture-invariance training term (ablation)global SSIM model · LIVE_AugSRCC: 0.881 -> 0.928Improved
add E2 texture-invariance training term (ablation)global SSIM model · TID2013SRCC: 0.835 -> 0.830Hurt
add E2 texture-invariance training term (ablation)global SSIM model · LIVESRCC: 0.957 -> 0.954Hurt
add E2 term to model without SSIM distance (ablation)LPIPS + input image · TID2013SRCC: 0.825 -> 0.776Hurt
DISTS vs LPIPS trained on BAPPSDISTS · BAPPS2AFC all: 0.689 vs 0.692No clear effect

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