LocateEdit-Bench: A Benchmark for Instruction-Based Editing Localization
Not on the map. Why?
Abstract (arXiv)
Recent advancements in image editing have enabled highly controllable and semantically-aware alteration of visual content, posing unprecedented challenges to manipulation localization. However, existing AI-generated forgery localization methods primarily focus on inpainting-based manipulations, making them ineffective against the latest instruction-based editing paradigms. To bridge this critical gap, we propose LocateEdit-Bench, a large-scale dataset comprising 231K edited images, designed specifically to benchmark localization methods against instruction-driven image editing. Our dataset incorporates four cutting-edge editing models and covers three common edit types. We conduct a detailed analysis of the dataset and develop two multi-metric evaluation protocols to assess existing localization methods. Our work establishes a foundation to keep pace with the evolving landscape of image editing, thereby facilitating the development of effective methods for future forgery localization. Dataset will be open-sourced upon acceptance.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 5 Feb 2026.
Builds on
25 of 34 references.
References · 25
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
- 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
- 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
- 2025Qwen3-VL Technical Reportcited by 2,534
- 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
- 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
- 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
- 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
- 2025Qwen-Image Technical Reportcited by 973
13 more
- 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
- 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
- 2025SAM 3: Segment Anything with Conceptscited by 835
- 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
- 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
- 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 417
- 2024OmniEdit: Building Image Editing Generalist Models Through Specialist Supervisioncited by 145
- 2021PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localizationcited by 133
- 2022ObjectFormer for Image Manipulation Detection and Localizationcited by 78
- 2023AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensicscited by 46
- 2024Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localizationcited by 35
- 2023Rethinking Image Editing Detection in the Era of Generative AI Revolutioncited by 21
- 2024GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localizationcited by 19
Built on by
Citing papers per year: 2026: 2.
2 papers.