用提升分数优化扩散模型的组合生成，让图像更符合多条件描述。
Improving Compositional Generation with Diffusion Models Using Lift Scores
- 基于提升分数重采样，评估生成结果是否满足单个条件。
- 在合成数据、位置任务和文生图任务中显著提升条件对齐度。
- 无需额外训练，推理开销低，适合实际应用部署。
我们提出一种基于提升分数的新重采样准则，用于改善扩散模型中的组合生成。通过提升分数，评估生成样本是否符合单一条件，并综合结果判断组合提示是否满足。核心洞察是：提升分数可仅用原始扩散模型高效近似，无需额外训练或外部模块。我们设计了一种优化变体，在推理时保持较低计算开销的同时仍具有效性。大量实验表明，提升分数显著提升了2D合成数据、CLEVR位置任务以及文本到图像合成中的条件对齐效果。代码已公开于 http://rainorangelemon.github.io/complift。
原文摘要 · Abstract (English)
We introduce a novel resampling criterion using lift scores, for improving compositional generation in diffusion models. By leveraging the lift scores, we evaluate whether generated samples align with each single condition and then compose the results to determine whether the composed prompt is satisfied. Our key insight is that lift scores can be efficiently approximated using only the original diffusion model, requiring no additional training or external modules. We develop an optimized variant that achieves relatively lower computational overhead during inference while maintaining effectiveness. Through extensive experiments, we demonstrate that lift scores significantly improved the condition alignment for compositional generation across 2D synthetic data, CLEVR position tasks, and text-to-image synthesis. Our code is available at http://rainorangelemon.github.io/complift.
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。