AI Paper Atlas

Research map / Image generation / Editing and style transfer

Exploring Stroke-Level Modifications for Scene Text Editing

Yadong Qu, Qingfeng Tan, Hongtao Xie, Jianjun Xu, YuXin Wang, Yongdong Zhang

AAAI 2023 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 34 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
add Stroke-Level Modification (ablation)MOSTEL · Tamper-SceneSeqAcc: 70.395 -> 76.790Improved
add recognizer supervision (ablation)MOSTEL · Tamper-SceneSeqAcc: 68.375 -> 76.790Improved
add Background Filtering (ablation)MOSTEL · Tamper-SceneSeqAcc: 72.362 -> 76.790Improved
add Style Augmentation (ablation)MOSTEL · Tamper-SceneSeqAcc: 26.408 -> 76.790Improved
block gradient propagation between BRM and TMM decoders (ablation)MOSTEL · Tamper-SceneSeqAcc: 25.670 -> 76.790Improved
apply SLM in TMM during training (ablation)MOSTEL · Tamper-SceneSeqAcc: 76.790 -> 70.032Hurt
add real images to semi-supervised training (1 image per batch) (ablation)MOSTEL · Tamper-SceneSeqAcc: 68.906 -> 75.353Improved
increase real images per batch from 1 to 2 (ablation)MOSTEL · Tamper-SceneSeqAcc: 75.353 -> 76.790Improved
increase real images per batch from 2 to 4 (ablation)MOSTEL · Tamper-SceneSeqAcc: 76.790 -> 68.220Hurt
train with SLM only in BRM rather than also in TMM (ablation)MOSTEL · Tamper-Syn2kFID: 30.66 -> 29.48Improved
use MOSTEL instead of SwapTextscene text editing · Tamper-Syn2kFID: 35.62 -> 29.48Improved
use MOSTEL instead of SwapTextscene text editing · Tamper-SceneSeqAcc: 60.634 -> 76.790Improved

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