AI Paper Atlas

Research map / Image generation / Image restoration

Image Harmonization With Transformer

Zonghui Guo, Dongsheng Guo, Haiyong Zheng, Zhaorui Gu, Bing Zheng, Junyu Dong

ICCV 2021 · Image generation › Image restoration · approach: Real-world restoration with unaligned data · 84 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 CNN harmonizer with Transformer-encoder HTE-D CNN · iHarmony4 (all)fMSE: 625.67 -> 395.66Improved
add disentanglement (reflectance/illumination) with TransformersHT · iHarmony4 (all)fMSE: 395.66 -> 320.78Improved
increase token number from N to 16N (stride 8 to 2), FC embedding (ablation)Transformer on iHarmony4 · iHarmony4 (all), 1-head 3-layer TREfMSE: 611.25 -> 447.64Improved
change embedding type from FC to CNN at T=4N (ablation)Transformer on iHarmony4 · iHarmony4 (all), 1-head 3-layer TREfMSE: 522.84 -> 520.19No clear effect
increase TRE layers from 3 to 9 (1 head) (ablation)HT · iHarmony4 (all)fMSE: 502.37 -> 415.60Improved
increase TRE layers from 9 to 12 (1 head) (ablation)HT · iHarmony4 (all)fMSE: 415.60 -> 419.08No clear effect
increase attention heads from 1 to 4 at 9 layers (ablation)HT · iHarmony4 (all)fMSE: 415.60 -> 392.74Improved
add Transformer decoder layers to encoder (E(3)+D(6) vs E(9)) (ablation)HT · iHarmony4 (all)fMSE: 415.60 -> 403.76No clear effect
use Transformer for reflectance pathway instead of CNN (ablation)D-HT · iHarmony4 (all)fMSE: 479.94 -> 352.55Improved
use Transformer for illumination pathway instead of CNN (ablation)D-HT · iHarmony4 (all)fMSE: 479.94 -> 348.80Improved
use Transformers in both pathways (ablation)D-HT · iHarmony4 (all)fMSE: 479.94 -> 320.78Improved
apply HT to inpainting vs RFR-NetHT · Paris StreetView inpaintingPSNR: 28.42 -> 29.55Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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