LVLM-Composer：面向图像生成的显式规划
LVLM-Composer's Explicit Planning for Image Generation
AI总结：
本文提出100亿参数模型LVLM-Composer，通过分层语义规划、细粒度特征对齐及带自校正的组合规划强化学习，显著提升复杂文本到图像生成中的组合准确性。
摘要：
生成式人工智能的快速发展从根本上重塑了内容创作方式，其中大型视觉语言模型（LVLMs）处于前沿地位。尽管当前的LVLMs在文本到图像生成方面已展现出令人瞩目的能力，但当面对需要精确组合理解和视觉规划的复杂文本描述时，它们往往表现不佳。这一局限性尤其影响在复杂场景中准确渲染多个对象、其属性、空间关系以及特定姿态的能力，LongBench-T2I等基准测试已证实了这一点。为应对这些挑战，我们提出了LVLM-Composer，这是一种新型的100亿参数规模LVLM，专门为增强组合式图像合成而设计。我们的方法包含一个分层语义规划模块，用于结构化提示分解，以及一个细粒度特征对齐机制，用于在生成过程中提供精确的视觉引导。我们提出了一种多阶段训练范式，包括分层语义-视觉对齐预训练和带自校正的组合规划强化学习，以培养鲁棒的组合推理能力。在LongBench-T2I基准上的大量实验——利用Gemini-2.0-Flash和InternVL3-78B进行自动评估——表明LVLM-Composer在对象准确性、组合保真度和姿态准确性等关键组合维度上具有卓越性能，显著优于最先进的基线方法。深入的消融研究进一步验证了所提模块不可或缺的贡献，同时人工评估确认了生成图像在感知质量上的优越性。LVLM-Composer代表了向真正可控且组合精确的开放式文本到图像生成迈出的重要一步。
英文摘要：
The burgeoning field of generative artificial intelligence has fundamentally reshaped our approach to content creation, with Large Vision-Language Models (LVLMs) standing at its forefront. While current LVLMs have demonstrated impressive capabilities in text-to-image generation, they often falter when confronted with complex textual descriptions demanding precise compositional understanding and visual planning. This limitation particularly impacts the accurate rendering of multiple objects, their attributes, spatial relationships, and specific poses within intricate scenes, as evidenced by benchmarks like LongBench-T2I. To address these challenges, we introduce LVLM-Composer, a novel 10-billion parameter scale LVLM specifically engineered for enhanced compositional image synthesis. Our method incorporates a Hierarchical Semantic Planning Module for structured prompt decomposition and a Fine-Grained Feature Alignment Mechanism for precise visual guidance during generation. We propose a multi-stage training paradigm, featuring Hierarchical Semantic-Visual Grounding Pre-training and Compositional Planning Reinforcement Learning with Self-Correction, to instill robust compositional reasoning. Extensive experiments on the LongBench-T2I benchmark, utilizing automatic evaluation by Gemini-2.0-Flash and InternVL3-78B, demonstrate LVLM-Composer's superior performance across critical compositional dimensions including object accuracy, composition fidelity, and pose accuracy, significantly outperforming state-of-the-art baselines. An in-depth ablation study further validates the indispensable contribution of our proposed modules, while human evaluations confirm the perceptual superiority of our generated images. LVLM-Composer represents a significant step towards truly controllable and compositionally accurate open-ended text-to-image generation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
