LatentCRF：用于高效潜在扩散的连续CRF
LatentCRF: Continuous CRF for Efficient Latent Diffusion
AI总结：
针对LDM多次推理迭代导致延迟的问题，提出作为神经网络层的连续CRF模型LatentCRF，通过建模潜在向量间关系替代部分计算密集的推理迭代，在无质量和多样性损失下将推理效率提升33%，且无需修改原LDM。
摘要：
Latent Diffusion Models (LDMs)（潜在扩散模型）能生成高质量、逼真的图像，然而，多次高昂的计算推理迭代所产生的延迟会限制其适用性。我们引入了LatentCRF，这是一种连续Conditional Random Field (CRF)（条件随机场）模型，作为神经网络层实现，用于建模LDM中潜在向量间的空间和语义关系。通过用我们轻量级的LatentCRF替代部分计算密集的LDM推理迭代，我们在质量、速度和多样性之间实现了更优的平衡。与完整的LDM相比，我们将推理效率提高了33%，且图像质量或多样性没有损失。LatentCRF是一个易于使用的附加组件，不需要修改LDM。
英文摘要：
Latent Diffusion Models (LDMs) produce high-quality, photo-realistic images, however, the latency incurred by multiple costly inference iterations can restrict their applicability. We introduce LatentCRF, a continuous Conditional Random Field (CRF) model, implemented as a neural network layer, that models the spatial and semantic relationships among the latent vectors in the LDM. By replacing some of the computationally-intensive LDM inference iterations with our lightweight LatentCRF, we achieve a superior balance between quality, speed and diversity. We increase inference efficiency by 33% with no loss in image quality or diversity compared to the full LDM. LatentCRF is an easy add-on, which does not require modifying the LDM.
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。
