Manifold Preserving Guided Diffusion
ICLR 2024(2023)
摘要
Despite the recent advancements, conditional image generation still faces
challenges of cost, generalizability, and the need for task-specific training.
In this paper, we propose Manifold Preserving Guided Diffusion (MPGD), a
training-free conditional generation framework that leverages pretrained
diffusion models and off-the-shelf neural networks with minimal additional
inference cost for a broad range of tasks. Specifically, we leverage the
manifold hypothesis to refine the guided diffusion steps and introduce a
shortcut algorithm in the process. We then propose two methods for on-manifold
training-free guidance using pre-trained autoencoders and demonstrate that our
shortcut inherently preserves the manifolds when applied to latent diffusion
models. Our experiments show that MPGD is efficient and effective for solving a
variety of conditional generation applications in low-compute settings, and can
consistently offer up to 3.8x speed-ups with the same number of diffusion steps
while maintaining high sample quality compared to the baselines.
更多查看译文
关键词
generative model,diffusion model,controllable generation
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要