解决文本生成多人图像时的身份混乱问题
Resolving the Identity Crisis in Text-to-Image Generation
- 用强化学习直接优化图像内与跨样本的身份多样性
- 在DiverseHumans数据集上实现98.6%唯一人脸准确率
- 无需真实数据，适合需要多角色生成的场景
当前最先进的文生图模型在生成多人场景时存在持续的身份危机：出现重复人脸、身份融合和人数误判。我们提出DisCo（基于多样性约束的强化学习框架），通过组相对策略优化（GRPO）微调流匹配模型，利用组合奖励函数实现：(i) 惩罚图像内面部相似性，(ii) 避免样本间身份重复，(iii) 确保准确的人数生成，(iv) 通过人类偏好得分保持视觉质量和提示一致性。单阶段课程训练稳定应对提示复杂度提升。该方法无需真实数据。在DiverseHumans测试集上，DisCo达到98.6%的唯一人脸准确率和近乎完美的全局身份分布，优于开源及专有模型（如Gemini、GPT-Image），同时保持感知质量。结果表明，跨样本多样性是解决身份坍缩的关键，使DisCo成为可扩展、无需标注的多人图像生成方案。
原文摘要 · Abstract (English)
State-of-the-art text-to-image models suffer from a persistent identity crisis when generating scenes with multiple humans: producing duplicate faces, merging identities, and miscounting individuals. We present DisCo (Reinforcement with Diversity Constraints), a reinforcement learning framework that directly optimizes identity diversity both within images and across groups of generated samples. DisCo fine-tunes flow-matching models using Group-Relative Policy Optimization (GRPO), guided by a compositional reward that: (i) penalizes facial similarity within images, (ii) discourages identity repetition across samples, (iii) enforces accurate person counts, and (iv) preserves visual fidelity and prompt alignment via human preference scores. A single-stage curriculum stabilizes training as prompt complexity increases. Importantly, this method does not require any real data. On the DiverseHumans Testset, DisCo achieves 98.6% Unique Face Accuracy and near-perfect Global Identity Spread, outperforming open-source and proprietary models (e.g., Gemini, GPT-Image) while maintaining perceptual quality. Our results establish cross-sample diversity as a critical axis for resolving identity collapse, positioning DisCo as a scalable, annotation-free solution for multi-human image synthesis. Project page: https://qualcomm-ai-research.github.io/disco/
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。