EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing

• URL: http://arxiv.org/abs/2603.14916v1
• Date: Mon, 16 Mar 2026 07:24:56 GMT
• Title: EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing
• Abstract summary: We present textbfEditHF-1M, a million-scale image editing dataset with over 29M human preference pairs and 148K human mean opinion ratings.<n>We also introduce textbfEditHF-Reward, which utilizes EditHF as the reward signal to optimize the text-guided image editing models.
• Score: 80.4661213011098
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent text-guided image editing (TIE) models have achieved remarkable progress, while many edited images still suffer from issues such as artifacts, unexpected editings, unaesthetic contents. Although some benchmarks and methods have been proposed for evaluating edited images, scalable evaluation models are still lacking, which limits the development of human feedback reward models for image editing. To address the challenges, we first introduce \textbf{EditHF-1M}, a million-scale image editing dataset with over 29M human preference pairs and 148K human mean opinion ratings, both evaluated from three dimensions, \textit{i.e.}, visual quality, instruction alignment, and attribute preservation. Based on EditHF-1M, we propose \textbf{EditHF}, a multimodal large language model (MLLM) based evaluation model, to provide human-aligned feedback from image editing. Finally, we introduce \textbf{EditHF-Reward}, which utilizes EditHF as the reward signal to optimize the text-guided image editing models through reinforcement learning. Extensive experiments show that EditHF achieves superior alignment with human preferences and demonstrates strong generalization on other datasets. Furthermore, we fine-tune the Qwen-Image-Edit using EditHF-Reward, achieving significant performance improvements, which demonstrates the ability of EditHF to serve as a reward model to scale-up the image editing. Both the dataset and code will be released in our GitHub repository: https://github.com/IntMeGroup/EditHF.

Related papers

• MIEScore: Human-Aligned Evaluation for Multi-Source Image Editing [80.57428909397176]
  We introduce MIE-Bench, the first large-scale multiple image editing benchmark with fine-grained human preference annotations.<n>MIE-Bench includes 3,000 editing instances across 16 tasks, each involving more than two source images and an editing prompt.<n>MIEScore is a multimodal large language model (MLLM)-based evaluation model enhanced with skill optimization and multi-dimensional supervised fine-tuning.
  arXiv  Detail & Related papers  (2026-08-03T10:57:00Z)
• ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning [86.61218827780675]
  We present ReasonEdit, an evaluation tool for text-guided image editing.<n>It is trained using reward signals derived from RE-Reward and the Group Relative Policy Optimization (GRPO) algorithm.<n>It is capable of generating high-quality interpretable evaluation text, enabling more transparent and trustworthy assessment for image editing.
  arXiv  Detail & Related papers  (2026-05-08T09:23:26Z)
• Leveraging Verifier-Based Reinforcement Learning in Image Editing [41.64251379221566]
  We introduce Edit-R1, a framework that builds a chain-of-thought (CoT) verifier-based reasoning reward model (RRM) for downstream image editing.<n>Our experiments demonstrate that our Edit-RRM surpasses powerful VLMs as an editing-specific reward model.
  arXiv  Detail & Related papers  (2026-04-30T06:54:39Z)
• Understanding the Implicit User Intention via Reasoning with Large Language Model for Image Editing [23.69189799564107]
  Existing image editing methods can handle simple editing instructions very well.<n>To deal with complex editing instructions, they often need to jointly fine-tune the large language models (LLMs) and diffusion models (DMs)<n>We propose a new method, called textbfComplex textbfImage textbfEditing via textbfLLM textbfReasoning (CIELR), which converts a complex user instruction into a set of simple and explicit editing actions.
  arXiv  Detail & Related papers  (2025-10-31T10:06:28Z)
• Visual Autoregressive Modeling for Instruction-Guided Image Editing [97.04821896251681]
  We present a visual autoregressive framework that reframes image editing as a next-scale prediction problem.<n>VarEdit generates multi-scale target features to achieve precise edits.<n>It completes a $512times512$ editing in 1.2 seconds, making it 2.2$times$ faster than the similarly sized UltraEdit.
  arXiv  Detail & Related papers  (2025-08-21T17:59:32Z)
• LMM4Edit: Benchmarking and Evaluating Multimodal Image Editing with LMMs [104.97913324464247]
  We introduce EBench-18K, the first large-scale image Editing Benchmark including 18K edited images with fine-grained human preference annotations.<n>EBench-18K includes 1,080 source images with corresponding editing prompts across 21 tasks, 18K+ edited images produced by 17 state-of-the-art TIE models, 55K+ mean opinion scores (MOSs) assessed from three evaluation dimensions, and 18K+ question-answering (QA) pairs.<n>Then, we propose LMM4Edit, a LMM-based metric for evaluating image Editing models from perceptual quality, editing alignment, attribute preservation
  arXiv  Detail & Related papers  (2025-07-22T03:11:07Z)
• GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing [60.66800567924348]
  We introduce a new benchmark designed to evaluate text-guided image editing models.<n>The benchmark includes over 1000 high-quality editing examples across 20 diverse content categories.<n>We conduct a large-scale study comparing GPT-Image-1 against several state-of-the-art editing models.
  arXiv  Detail & Related papers  (2025-05-16T17:55:54Z)
• Forgedit: Text Guided Image Editing via Learning and Forgetting [17.26772361532044]
  We design a novel text-guided image editing method, named as Forgedit. First, we propose a vision-language joint optimization framework capable of reconstructing the original image in 30 seconds. Then, we propose a novel vector projection mechanism in text embedding space of Diffusion Models.
  arXiv  Detail & Related papers  (2023-09-19T12:05:26Z)
• HIVE: Harnessing Human Feedback for Instructional Visual Editing [127.29436858998064]
  We present a novel framework to harness human feedback for instructional visual editing (HIVE) Specifically, we collect human feedback on the edited images and learn a reward function to capture the underlying user preferences. We then introduce scalable diffusion model fine-tuning methods that can incorporate human preferences based on the estimated reward.
  arXiv  Detail & Related papers  (2023-03-16T19:47:41Z)

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.