让文字生成图像更准：用逻辑条件自动纠错，效率提升超七成。
EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
- 将提示分解为可验证的逻辑条件，按失败情况分步精准修正。
- 在GenEval2上准确率从34.16%提升至71.46%，显著优于现有方法。
- 无需训练，推理时高效调整，适合对生成精度要求高的场景。
近期文本到图像（T2I）生成器虽能合成逼真图像，但在涉及多个物体、数量、属性及关系的组合式提示下仍表现不佳。本文提出EPIC（高效谓词引导的推理时控制），一种无需训练的推理时优化框架，用于提升组合式T2I生成效果。EPIC将优化过程建模为谓词引导的搜索：一次性解析原始提示为包含对象变量和类型谓词的固定视觉程序，覆盖可验证的条件如物体存在性、数量、属性与关系。每张生成或编辑后的图像均通过提取自该图像的视觉证据进行验证。仅当所有谓词满足时，图像才被视为符合提示；否则，失败的谓词决定下一步操作，局部失败导向针对性编辑，全局失败导向重采样，而视觉程序保持不变。在GenEval2测试中，EPIC将单次生成的提示级准确率从基础生成器的34.16%提升至71.46%。在相同生成器/编辑器设置和最大图像模型执行预算下，相比最强基线，EPIC提升19.23个百分点准确率，同时减少31%的图像模型调用、72%的多模态大模型（MLLM）调用和81%的MLLM token消耗。
原文摘要 · Abstract (English)
Recent text-to-image (T2I) generators can synthesize realistic images, but still struggle with compositional prompts involving multiple objects, counts, attributes, and relations. We introduce EPIC (Efficient Predicate-Guided Inference-Time Control), a training-free inference-time refinement framework for compositional T2I generation. EPIC casts refinement as predicate-guided search: it parses the original prompt once into a fixed visual program of object variables and typed predicates, covering checkable conditions such as object presence, counts, attributes, and relations. Each generated or edited image is verified against this program using visual evidence extracted from that image. An image is judged to satisfy the prompt only when all predicates are satisfied; otherwise, failed predicates decide the next step, routing local failures to targeted editing and global failures to resampling while the fixed visual program remains unchanged. On GenEval2, EPIC improves prompt-level accuracy from 34.16% for single-pass generation with the base generator to 71.46%. Under the same generator/editor setting and maximum image-model execution budget, EPIC outperforms the strongest prior refinement baseline by 19.23 points while reducing realized cost by 31% in image-model executions, 72% in MLLM calls, and 81% in MLLM tokens per prompt.
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。