DEAL-300K: Diffusion-based Editing Area Localization with a 300K-Scale Dataset and Frequency-Prompted Baseline

• URL: http://arxiv.org/abs/2511.23377v1
• Date: Fri, 28 Nov 2025 17:22:07 GMT
• Title: DEAL-300K: Diffusion-based Editing Area Localization with a 300K-Scale Dataset and Frequency-Prompted Baseline
• Abstract summary: Diffusion-based image manipulation (DIML) enables realistic local forgeries that are hard to localize.<n>We present a large scale dataset for diffusion-based image localization (DIML) with more than 300,000 images.<n>We propose a localization framework that uses a frozen Visual Foundation Model (VFM) together with Multi Frequency Prompt Tuning (T) to capture both semantic and frequency cues.
• Score: 23.338550669094655
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion-based image editing has made semantic level image manipulation easy for general users, but it also enables realistic local forgeries that are hard to localize. Existing benchmarks mainly focus on the binary detection of generated images or the localization of manually edited regions and do not reflect the properties of diffusion-based edits, which often blend smoothly into the original content. We present Diffusion-Based Image Editing Area Localization Dataset (DEAL-300K), a large scale dataset for diffusion-based image manipulation localization (DIML) with more than 300,000 annotated images. We build DEAL-300K by using a multi-modal large language model to generate editing instructions, a mask-free diffusion editor to produce manipulated images, and an active-learning change detection pipeline to obtain pixel-level annotations. On top of this dataset, we propose a localization framework that uses a frozen Visual Foundation Model (VFM) together with Multi Frequency Prompt Tuning (MFPT) to capture both semantic and frequency-domain cues of edited regions. Trained on DEAL-300K, our method reaches a pixel-level F1 score of 82.56% on our test split and 80.97% on the external CoCoGlide benchmark, providing strong baselines and a practical foundation for future DIML research.The dataset can be accessed via https://github.com/ymhzyj/DEAL-300K.

Related papers

• DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection [48.00148913303519]
  Diffusion-based editing enables realistic modification of local image regions, making AI-generated content harder to detect.<n>We introduce DiffSeg30k, a dataset of 30k diffusion-edited images with pixel-level annotations to support fine-grained detection.
  arXiv  Detail & Related papers  (2025-11-24T13:43:54Z)
• FragFake: A Dataset for Fine-Grained Detection of Edited Images with Vision Language Models [48.85744313139525]
  We develop FragFake, the first dedicated benchmark dataset for edited image detection.<n>We use Vision Language Models (VLMs) for the first time in the task of edited image classification and edited region localization.<n>This work is the first to reformulate localized image edit detection as a vision-language understanding task.
  arXiv  Detail & Related papers  (2025-05-21T15:22:45Z)
• X-Edit: Detecting and Localizing Edits in Images Altered by Text-Guided Diffusion Models [3.610796534465868]
  Experimental results demonstrate that X-Edit accurately localizes edits in images altered by text-guided diffusion models.<n>This highlights X-Edit's potential as a robust forensic tool for detecting and pinpointing manipulations introduced by advanced image editing techniques.
  arXiv  Detail & Related papers  (2025-05-16T23:29:38Z)
• PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models [80.98455219375862]
  We present the first text-based image editing approach for object parts based on pre-trained diffusion models.<n>Our approach is preferred by users 66-90% of the time in conducted user studies.
  arXiv  Detail & Related papers  (2025-02-06T13:08:43Z)
• EditScout: Locating Forged Regions from Diffusion-based Edited Images with Multimodal LLM [50.054404519821745]
  We present a novel framework that integrates a multimodal Large Language Model for enhanced reasoning capabilities.<n>Our framework achieves promising results on MagicBrush, AutoSplice, and PerfBrush datasets.<n> Notably, our method excels on the PerfBrush dataset, a self-constructed test set featuring previously unseen types of edits.
  arXiv  Detail & Related papers  (2024-12-05T02:05:33Z)
• LIME: Localized Image Editing via Attention Regularization in Diffusion Models [69.33072075580483]
  This paper introduces LIME for localized image editing in diffusion models.<n>LIME does not require user-specified regions of interest (RoI) or additional text input, but rather employs features from pre-trained methods and a straightforward clustering method to obtain precise editing mask.<n>We propose a novel cross-attention regularization technique that penalizes unrelated cross-attention scores in the RoI during the denoising steps, ensuring localized edits.
  arXiv  Detail & Related papers  (2023-12-14T18:59:59Z)
• Weakly-supervised deepfake localization in diffusion-generated images [4.548755617115687]
  We propose a weakly-supervised localization problem based on the Xception network as the backbone architecture. We show that the best performing detection method (based on local scores) is less sensitive to the looser supervision than to the mismatch in terms of dataset or generator.
  arXiv  Detail & Related papers  (2023-11-08T10:27:36Z)
• iEdit: Localised Text-guided Image Editing with Weak Supervision [53.082196061014734]
  We propose a novel learning method for text-guided image editing. It generates images conditioned on a source image and a textual edit prompt. It shows favourable results against its counterparts in terms of image fidelity, CLIP alignment score and qualitatively for editing both generated and real images.
  arXiv  Detail & Related papers  (2023-05-10T07:39:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.