SCOPE：结构分解与条件技能协调用于复杂图像生成
SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
AI总结：
本文提出SCOPE框架，通过结构化规范和条件技能协调解决复杂图像生成中语义承诺的持续跟踪问题，通过Gen-Arena基准验证其有效性，取得优于基线的性能。
摘要：
尽管文本到图像模型在视觉保真度上取得了显著进展，但忠实实现复杂的视觉意图仍具挑战性，因为许多要求必须跨接地、生成和验证过程跟踪。我们称这些要求为语义承诺，并正式化其生命周期断续性为概念裂痕，其中承诺可能局部解决或检查，但无法在整个生成生命周期中保持可识别的同一操作单元。为了解决这个问题，我们提出了SCOPE，一个由规范引导的技能协调框架，通过演进的结构化规范维护语义承诺，并在未解决或违反承诺时有条件地调用检索、推理和修复技能。为了评估承诺层面的意图实现，我们引入了Gen-Arena，一个带有实体和约束级别规范的人工标注基准，以及实体门控意图通过率（EGIP），一个严格的先实体通过标准。SCOPE在Gen-Arena上显著优于所有评估基线，达到0.60 EGIP，并在WISE-V（0.907）和MindBench（0.61）上进一步取得强劲结果，证明了持续跟踪承诺对于复杂图像生成的有效性。
英文摘要：
While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual intents remains challenging because many requirements must be tracked across grounding, generation, and verification. We refer to these requirements as semantic commitments and formalize their lifecycle discontinuity as the Conceptual Rift, where commitments may be locally resolved or checked but fail to remain identifiable as the same operational units throughout the generation lifecycle. To address this, we propose SCOPE, a specification-guided skill orchestration framework that maintains semantic commitments in an evolving structured specification and conditionally invokes retrieval, reasoning, and repair skills around unresolved or violated commitments. To evaluate commitment-level intent realization, we introduce Gen-Arena, a human-annotated benchmark with entity- and constraint-level specifications, together with Entity-Gated Intent Pass Rate (EGIP), a strict entity-first pass criterion. SCOPE substantially outperforms all evaluated baselines on Gen-Arena, achieving 0.60 EGIP, and further achieves strong results on WISE-V (0.907) and MindBench (0.61), demonstrating the effectiveness of persistent commitment tracking for complex 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。
