Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
121 tokens/sec
GPT-4o
9 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Efficient Flow Matching using Latent Variables (2505.04486v2)

Published 7 May 2025 in cs.CV, cs.AI, and cs.LG

Abstract: Flow matching models have shown great potential in image generation tasks among probabilistic generative models. However, most flow matching models in the literature do not explicitly model the underlying structure/manifold in the target data when learning the flow from a simple source distribution like the standard Gaussian. This leads to inefficient learning, especially for many high-dimensional real-world datasets, which often reside in a low-dimensional manifold. Existing strategies of incorporating manifolds, including data with underlying multi-modal distribution, often require expensive training and hence frequently lead to suboptimal performance. To this end, we present $\texttt{Latent-CFM}$, which provides simplified training/inference strategies to incorporate multi-modal data structures using pretrained deep latent variable models. Through experiments on multi-modal synthetic data and widely used image benchmark datasets, we show that $\texttt{Latent-CFM}$ exhibits improved generation quality with significantly less training (up to $\sim 50\%$ less) and computation than state-of-the-art flow matching models by incorporating extracted data features using pretrained lightweight latent variable models. Moving beyond natural images to generating fields arising from processes governed by physics, using a 2d Darcy flow dataset, we demonstrate that our approach generates more physically accurate samples than competitive approaches. In addition, through latent space analysis, we demonstrate that our approach can be used for conditional image generation conditioned on latent features, which adds interpretability to the generation process.

Summary

We haven't generated a summary for this paper yet.