佛山科学技术学院学报（自然科学版）2026，Vol.44Issue(3)：33-40,8.
面向人-物交互场景的图像生成框架研究
Research on image generation framework for human-object interaction scenarios
摘要
Abstract
Existing Human-Object Interaction(HOI)text-to-image methods remain limited in modeling fine-grained interactions and achieving coherent foreground-background fusion.To address this,we propose a HOI-oriented image generation framework built upon a three-stage architecture.First,a text semantic reconstruction mechanism is introduced,where a large language model performs structured parsing and stage-wise reorganization of the input description to enhance alignment between attribute expression and interaction semantics.Next,a subject-object prior fusion module jointly models masks and latent representations of subjects and objects by integrating textual semantics with geometric priors,improving interaction modeling and structural consistency.Experiments on an interaction dataset constructed from T2I-CompBench demonstrate superior performance,achieving CLIP-Score 28.41,Verb CLIP-Score 21.06,and a user-preference-based PickScore of 20.22,validating the effectiveness of the proposed method in both generation quality and interaction representation.关键词
人-物交互/文本语义重构/大语言模型/先验融合/图像生成Key words
human-object interaction/text semantic reconstruction/large language model/prior fusion/image generation分类
信息技术与安全科学引用本文复制引用
周燕,陈维德,彭俊轩,刘翔宇,周月霞..面向人-物交互场景的图像生成框架研究[J].佛山科学技术学院学报（自然科学版）,2026,44(3):33-40,8.基金项目
国家自然科学基金资助项目(61972091) （61972091）
