AI Paper Atlas

Research map / Image generation / Editing and style transfer

Semantically Aligned Gradient-Driven Context-Preserving Image Editing

Chiranjeev Chiranjeev, Muskan Dosi, MAYANK VATSA, RICHA SINGH

ECCV 2026 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 0 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 distillation loss L_D (gradient-enabled VLM supervision) to denoising loss (ablation)IABEdit · RealEditharmonic mean (CLIP-T, CS-P): +2.47 HMImproved
add LoRA adaptation to the Instruction Aligner (ablation)IABEdit · RealEditharmonic mean (CLIP-T, CS-P): +4.42 HMImproved
replace LLaVA-7B with Qwen-VL-2.5-7B (ablation)IABEdit · RealEditharmonic mean (CLIP-T, CS-P): 42.00 -> 42.27Improved
add context-preservation conditioning (ablation)IABEdit · RealEditharmonic mean (CLIP-T, CS-P): +1.81 HMImproved
raise timestep threshold tau from 200 to 300 (ablation)IABEdit · RealEditharmonic mean (CLIP-T, CS-P): 42.00 -> 40.67Hurt
add distillation loss L_D on D-LORD (ablation)IABEdit · D-LORD (face editing)harmonic mean (CLIP-T, CS-P): 41.71 -> 44.68Improved
add identity coherence loss L_C (ablation)IABEdit · D-LORD (face editing)DINO-P: 53.59 -> 55.33Improved
train FLUX.1 with IABEditFLUX.1 Kontext Dev · RealEditharmonic mean (CLIP-T, CS-P): 41.29 -> 42.28Improved
IABEdit vs best diffusion baseline UltraEditIABEdit · MagicBrushDINO-I: 84.77 -> 88.26Improved
IABEdit vs SuperEdit on GPT-4o overall ratingIABEdit · RealEdit (GPT-4o)overall score: 3.91 -> 3.78Hurt
IABEdit vs Gemini-AI agent on identity preservationIABEdit · D-LORD (face editing)DINO-P: 50.20 -> 55.33Improved
IABEdit vs SuperEdit on CS-PIABEdit · RealEditCS-P: 90.93 -> 89.65Hurt

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