Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation
For practitioners of diffusion models, ALM provides a versatile, efficient, and high-quality solution for content generation from partial inputs, overcoming limitations of both training-based and training-free approaches.
ALM introduces a training-free sampling strategy that directly optimizes unobserved variables during reverse diffusion, achieving globally coherent generation across diverse tasks and domains, outperforming state-of-the-art methods.
Generating diverse, coherent, and plausible content from partially given inputs remains a fundamental challenge for diffusion models. Existing approaches face clear limitations: training-based approaches offer strong task-specific results but require costly computation, and they generalize poorly across tasks. Training-free approaches offer better efficiency, but they do not explicitly optimize over unobserved variables, leading to globally inconsistent results. To address these limitations, we introduce Accelerated Likelihood Maximization (ALM), a novel training-free sampling strategy integrated into the reverse diffusion process that significantly extends the applicability of diffusion models beyond simple generation tasks. Unlike previous methods that implicitly influence missing regions through pre-generated region constraints, we directly optimize the unobserved region during the sampling process, enabling globally coherent and plausible generation. Furthermore, we incorporate an acceleration strategy that significantly improves computational efficiency without sacrificing performance. Experimental results demonstrate that ALM consistently outperforms state-of-the-art methods in various data domains and tasks, establishing a powerful paradigm for versatile content generation.