AI Paper Atlas

Research map / Image generation / Editing and style transfer

T-Edit: Triple-Branch Diffusion Anchoring for Consistent Editing

Linsong Shan, Laurence Tianruo Yang, Zecan Yang, Shijie Lian, shijie lv, Qilin Yang

ICML 2026 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing

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 reconstruction-based error correction (ablation)T-Edit base · PIE-BenchLPIPS: 0.2270 -> 0.1540Improved
add reconstruction-based error correction (ablation)T-Edit base · PIE-BenchCLIP score: 31.12 -> 30.75Hurt
add reconstruction-based error correction (ablation)T-Edit base · PIE-BenchPSNR: 18.54 -> 19.22Improved
add feature injection at fixed vital layers (ablation)T-Edit with error correction · PIE-BenchPSNR: 19.22 -> 20.95Improved
add feature injection at fixed vital layers (ablation)T-Edit with error correction · PIE-BenchLPIPS: 0.1540 -> 0.1325Improved
replace fixed vital layers with dynamic vital layer localization (ablation)T-Edit · PIE-BenchPSNR: 20.95 -> 22.88Improved
replace fixed vital layers with dynamic vital layer localization (ablation)T-Edit · PIE-BenchLPIPS: 0.1325 -> 0.1237Improved
replace fixed vital layers with dynamic vital layer localization (ablation)T-Edit · PIE-BenchFID: 64.12 -> 64.15No clear effect
add TA frequency-aware injection in non-vital layers (ablation)T-Edit · PIE-BenchPSNR: 22.88 -> 23.89Improved
add TA frequency-aware injection in non-vital layers (ablation)T-Edit · PIE-BenchFID: 64.15 -> 62.22Improved
add TA frequency-aware injection in non-vital layers (ablation)T-Edit · PIE-BenchLPIPS: 0.1237 -> 0.1088Improved
use T-Edit instead of RF-Edit on videoHunyuanVideo · Video editing (Ditto-1M)FID: 68.45 -> 65.87Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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