提出新框架，让模型自动学习图像编辑质量评估标准与分数连续性。
Redefining Quality Criteria and Distance-Aware Score Modeling for Image Editing Assessment
- 用反馈优化提示词，自动改进评估指标定义。
- 通过距离感知损失，让分数变化更符合人类判断的连续规律。
- 无需额外数据，在竞赛中排名第四，适合质量评估研究者使用。
近期图像编辑技术的发展催生了对可靠图像编辑质量评估（IEQA）的需求。与传统方法不同，IEQA需对多模态输入进行复杂推理，并完成多维度评价。现有基于多模态大模型的方法常依赖人工启发式提示，存在指标提示僵化和距离无关的分数建模问题，导致与隐含的人类评判标准不一致，且无法捕捉分数空间的连续结构。为此，我们提出统一框架DS-IEQA，联合学习评估标准与分数表示。具体地，引入反馈驱动的度量提示优化（FDMPO），通过概率反馈自动优化度量定义；同时提出分词解耦的距离回归损失（TDRL），将数值标记与语言建模解耦，通过期望距离最小化显式建模分数连续性。大量实验表明，本方法性能优越：在未使用额外训练数据的情况下，于2026年NTIRE X-AIGC质量评估赛道2中排名第四。
原文摘要 · Abstract (English)
Recent advances in image editing have heightened the need for reliable Image Editing Quality Assessment (IEQA). Unlike traditional methods, IEQA requires complex reasoning over multimodal inputs and multi-dimensional assessments. Existing MLLM-based approaches often rely on human heuristic prompting, leading to two key limitations: rigid metric prompting and distance-agnostic score modeling. These issues hinder alignment with implicit human criteria and fail to capture the continuous structure of score spaces. To address this, we propose Define-and-Score Image Editing Quality Assessment (DS-IEQA), a unified framework that jointly learns evaluation criteria and score representations. Specifically, we introduce Feedback-Driven Metric Prompt Optimization (FDMPO) to automatically refine metric definitions via probabilistic feedback. Furthermore, we propose Token-Decoupled Distance Regression Loss (TDRL), which decouples numerical tokens from language modeling to explicitly model score continuity through expected distance minimization. Extensive experiments show our method's superior performance; it ranks 4th in the 2026 NTIRE X-AIGC Quality Assessment Track 2 without any additional training data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。