AI Paper Atlas

Research map / Image generation / Editing and style transfer

SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing

Ming Li, Xin Gu, Fan Chen, Xiaoying Xing, Longyin Wen, Chen Chen, Sijie Zhu

ICCV 2025 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 15 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 rectified editing instructions (40K) in place of original noisy instructions (ablation)InstructPix2Pix-style SD1.5 · Real-Editfollowing score: 2.45 -> 3.40Improved
add rectified editing instructions (ablation)InstructPix2Pix-style SD1.5 · Real-Editpreserving score: 3.27 -> 4.06Improved
add rectified editing instructions (ablation)InstructPix2Pix-style SD1.5 · Real-Editquality score: 3.90 -> 4.01Improved
add contrastive instructions with triplet loss to rectified instructions (ablation)SuperEdit · Real-Editfollowing score: 3.40 -> 3.59Improved
add contrastive instructions with triplet loss (ablation)SuperEdit · Real-Editpreserving score: 4.06 -> 4.14Improved
add contrastive instructions with triplet loss (ablation)SuperEdit · Real-Editquality score: 4.01 -> 4.01No clear effect
scale training data from 5k to 40k (ablation)SuperEdit · Real-Editoverall accuracy: 54.7% -> 69.7%Improved
scale training data from 10k to 20k (ablation)SuperEdit · Real-Editoverall score: 3.63 -> 3.79Improved
use GPT-4o instead of open-source VLMs for rectification (ablation)rectification pipeline · 100 samplesrectification success rate: 50.4% -> 76.2%Improved
initialize from InstructDiffusion weights instead of SD1.5 (ablation)SuperEdit · Real-Editpreserving accuracy: 77% -> 83%Improved
train at 256 resolution instead of 512 (ablation)SuperEdit · Real-Editpreserving accuracy: 77% -> 75%Mixed
use SuperEdit (40K data, no extra module) instead of SmartEditSmartEdit · Real-Editoverall score: 3.59 -> 3.91Improved

Later papers that compared with this method

2 later accepted papers report SuperEdit* as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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