AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models

Lorenzo Baraldi, Davide Bucciarelli, Federico Betti, Marcella Cornia, Lorenzo Baraldi, Nicu Sebe, Rita Cucchiara

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 3 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 stage 1 pretraining on similar real image pairs (ablation)DICE difference detector (Idefics3-8B) · DICE-D difference detection (class-agnostic)AP: 15.1 -> 16.7Improved
add stage 1 pretraining on similar real image pairs (ablation)DICE difference detector (Idefics3-8B) · DICE-D difference detection (class-aware)AP: 9.4 -> 10.6Improved
add stage 2 inpainting fine-tuning after stage 1 (ablation)DICE difference detector (Idefics3-8B) · DICE-D difference detection (class-agnostic)AP: 2.9 -> 22.3Improved
add extracted command-probability confidence instead of fixed value 1 (ablation)DICE difference detector (Idefics3-8B, both stages) · DICE-D difference detection (class-agnostic)AP: 16.7 -> 22.3Improved
add extracted confidence instead of fixed value 1 (stage 2 only) (ablation)DICE difference detector (Idefics3-8B) · DICE-D difference detection (class-agnostic)AP: 15.1 -> 18.2Improved
use extracted confidence instead of random confidence (ablation)DICE difference detector (Idefics3-8B) · DICE-D difference detection (class-agnostic)AP: 16.8 -> 22.3Improved
add extracted confidence in the coherence AP computation (ablation)DICE (Idefics3-8B) · DICE-D coherence estimation (detected areas)AP: 12.0 -> 15.5Improved
use Idefics3-8B instead of mPLUG-Owl3-7B as backboneDICE difference detector · DICE-D difference detection (class-agnostic)AP: 5.2 -> 22.3Improved
use Idefics3-8B instead of Qwen2-VL-7B as backboneDICE difference detector · DICE-D difference detection (class-agnostic)AP: 2.3 -> 22.3Improved
use Idefics3-8B instead of mPLUG-Owl3-7B as coherence estimatorDICE coherence estimation · DICE-D coherence estimation (detected areas)accuracy: 85.9 -> 85.4No clear effect
patch coherent differences in CLIP-I using DICECLIP-I · Correlation with human judgment, background preservationcorrelation rho: 51.1 -> 54.5Improved
patch all detected differences in CLIP-ICLIP-I · Correlation with human judgment, background preservationcorrelation rho: 51.1 -> 32.7Hurt

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