统一掩码图像生成与扩散模型，实现高效高质图像合成。
Effective and Efficient Masked Image Generation Models
- 将掩码生成与扩散模型整合至同一框架，优化训练与采样策略。
- 在ImageNet 256×256上，相同参数与推理步数下优于VAR模型。
- 相比顶尖连续扩散模型，仅需不足45%推理步数即可达到相当性能。
尽管掩码图像生成模型与掩码扩散模型的设计动机和目标不同，我们发现二者可在单一框架内统一。基于此洞察，我们系统探索了训练与采样设计空间，识别出影响性能与效率的关键因素。据此提出eMIGM模型。实验表明，eMIGM在ImageNet图像生成任务上表现优异，以弗雷切特起始距离（FID）衡量。尤其在ImageNet 256×256下，当函数评估次数（NFEs）与模型参数量相近时，eMIGM超越开创性模型VAR。随着NFE与参数量增加，eMIGM性能接近当前最优连续扩散模型REPA，但所需NFE低于其45%。此外，在ImageNet 512×512上，eMIGM优于强大连续扩散模型EDM2。代码已开源：https://github.com/ML-GSAI/eMIGM。
原文摘要 · Abstract (English)
Although masked image generation models and masked diffusion models are designed with different motivations and objectives, we observe that they can be unified within a single framework. Building upon this insight, we carefully explore the design space of training and sampling, identifying key factors that contribute to both performance and efficiency. Based on the improvements observed during this exploration, we develop our model, referred to as \textbf{eMIGM}. Empirically, eMIGM demonstrates strong performance on ImageNet generation, as measured by Fréchet Inception Distance (FID). In particular, on ImageNet $256\times256$, with similar number of function evaluations (NFEs) and model parameters, eMIGM outperforms the seminal VAR. Moreover, as NFE and model parameters increase, eMIGM achieves performance comparable to the state-of-the-art continuous diffusion model REPA while requiring less than 45\% of the NFE. Additionally, on ImageNet $512\times512$, eMIGM outperforms the strong continuous diffusion model EDM2. Code is available at https://github.com/ML-GSAI/eMIGM.
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。