无需重训练，让多个扩散模型协同生成并满足特定约束。
Projected Coupled Diffusion for Test-Time Constrained Joint Generation
- 引入耦合引导项和投影步骤，实现多模型协同生成
- 在图像对生成、物体操作等任务中达成强耦合与约束满足
- 适合需要快速调整生成结果的实时应用开发者
测试时采样修改已成为扩散模型的重要扩展，旨在不重新训练整个模型的前提下，引导生成过程以实现特定目标。然而，在不进行昂贵重训练的情况下，从多个预训练扩散模型中联合生成相关样本并同时施加任务特定约束仍具挑战性。为此，我们提出投影耦合扩散（Projected Coupled Diffusion, PCD），一种新型的测试时约束联合生成框架。PCD 在生成动态中引入耦合引导项，以促进不同扩散模型间的协调，并在每一步扩散过程中加入投影步骤，强制执行硬约束。实验表明，PCD 在图像对生成、物体操控及多机器人运动规划等应用场景中表现优异，实现了更强的耦合效果和保证的约束满足，且计算开销可控。
原文摘要 · Abstract (English)
Modifications to test-time sampling have emerged as an important extension to diffusion algorithms, with the goal of biasing the generative process to achieve a given objective without having to retrain the entire diffusion model. However, generating jointly correlated samples from multiple pre-trained diffusion models while simultaneously enforcing task-specific constraints without costly retraining has remained challenging. To this end, we propose Projected Coupled Diffusion (PCD), a novel test-time framework for constrained joint generation. PCD introduces a coupled guidance term into the generative dynamics to encourage coordination between diffusion models and incorporates a projection step at each diffusion step to enforce hard constraints. Empirically, we demonstrate the effectiveness of PCD in application scenarios of image-pair generation, object manipulation, and multi-robot motion planning. Our results show improved coupling effects and guaranteed constraint satisfaction without incurring excessive computational costs.
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。