发表机构
Hainan University; Guangdong Ocean University（海南大学; 广东海洋大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对可控曲线结构图像生成的挑战，提出CSGen模型，通过构建多领域数据集、分层渐进控制策略与稀疏感知损失机制，提升生成图像的结构精度与下游分割性能，为曲线结构分析提供新范式。
AI 中文摘要
曲线结构分析是多媒体领域一项重要且基础的任务，但生成带有精确曲线结构对象的可控图像仍是未解决的挑战。为解决该问题，本文提出CSGen，一种分层多模态扩散模型，可合成与多种控制条件精确对齐的高保真图像。CSGen基于三项关键创新构建：1）构建了多领域多模态数据集，包含来自5个领域的超24000个样本及7种不同类型的标注，用于训练统一生成模型；2）提出一种新型分层渐进控制策略，通过分阶段信号注入将拓扑线索与视觉上下文解耦，缓解语义漂移同时确保稀疏结构的拓扑完整性；3）设计了感知稀疏性的损失重加权机制，以应对曲线结构的极端稀疏性，在优化过程中显著增强对细薄脆弱结构的关注度。大量实验表明，CSGen生成的图像具有优异的结构精度和视觉真实感，在保持对不同提示的鲁棒性的同时，显著提升了下游分割性能。研究结果证实，CSGen是一种可扩展、以数据为中心的范式，适用于各类多媒体应用中复杂曲线结构的分析。代码和数据集可在指定网址获取。
英文摘要
Curvilinear structure analysis is an important and fundamental task in multimedia. However, the controllable generation of images with precise curvilinear structure objects remains an open challenge. To address this, we propose CSGen, a hierarchical multimodal diffusion model that synthesizes high-fidelity images precisely aligned with multiple control conditions. The CSGen is built upon three key innovations: 1) We construct a multi-domain and multimodal dataset, including over 24K samples from 5 domains and 7 different types of annotations, to train the unified generation model. 2) We propose a novel hierarchical progressive control strategy that decouples topology clues from visual context by a phased signal injection, mitigating semantic drift while ensuring the topological integrity of sparse structures. 3) We design a sparsity-aware loss re-weighting mechanism to address the extreme sparsity of curvilinear structures, significantly enhancing the attention on thin and fragile structures during optimization. Extensive experiments demonstrate that CSGen generates images with superior structure accuracy and visual realism, significantly improving downstream segmentation performance while maintaining robustness across diverse prompts. Our results confirm CSGen as a scalable, data-centric paradigm for the analysis of complex curvilinear structures in diverse multimedia applications. Code and dataset are available at https://github.com/ShanZard/CSGen.
CommentsAccepted to ACM MM 2026
