RPiAE：一种基于表示的自编码器，同时增强图像生成和编辑
RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing
AI总结：
本文提出RPiAE，一种基于表示的自编码器，通过引入表示偏转正则化和变分桥梁，提升图像生成和编辑的性能，实验表明其在文本到图像生成和图像编辑中表现优异。
摘要：
扩散模型已成为图像生成和编辑的主导范式，潜在扩散模型通过将去噪过程转移到紧凑的潜在空间以提高效率和可扩展性。最近尝试利用预训练视觉表示模型作为分词先验，要么对齐扩散特征与表示特征，要么直接重用表示编码器作为冻结的分词器。尽管这些方法可以提高生成指标，但冻结的编码器通常导致有限的重建保真度，从而降低编辑质量，以及过于高维的潜在空间使扩散建模困难。为了解决这些限制，我们提出了Representation-Pivoted AutoEncoder，一种基于表示的分词器，同时提升生成和编辑。我们引入了Representation-Pivot Regularization，一种训练策略，使表示初始化的编码器能够进行重建微调，同时保持预训练表示空间的语义结构，随后是变分桥梁，将潜在空间压缩成紧凑的空间以更好地进行扩散建模。我们采用了一个目标解耦的阶段式训练策略，依次优化生成可追溯性和重建保真度目标。这些组件共同产生了一个能够保持强语义、忠实重建并产生低扩散建模复杂度潜在的分词器。实验表明，RPiAE在文本到图像生成和图像编辑中优于其他视觉分词器，同时在表示基于的分词器中提供了最佳的重建保真度。
英文摘要：
Diffusion models have become the dominant paradigm for image generation and editing, with latent diffusion models shifting denoising to a compact latent space for efficiency and scalability. Recent attempts to leverage pretrained visual representation models as tokenizer priors either align diffusion features to representation features or directly reuse representation encoders as frozen tokenizers. Although such approaches can improve generation metrics, they often suffer from limited reconstruction fidelity due to frozen encoders, which in turn degrades editing quality, as well as overly high-dimensional latents that make diffusion modeling difficult. To address these limitations, We propose Representation-Pivoted AutoEncoder, a representation-based tokenizer that improves both generation and editing. We introduce Representation-Pivot Regularization, a training strategy that enables a representation-initialized encoder to be fine-tuned for reconstruction while preserving the semantic structure of the pretrained representation space, followed by a variational bridge which compress latent space into a compact one for better diffusion modeling. We adopt an objective-decoupled stage-wise training strategy that sequentially optimizes generative tractability and reconstruction-fidelity objectives. Together, these components yield a tokenizer that preserves strong semantics, reconstructs faithfully, and produces latents with reduced diffusion modeling complexity. Experiments demonstrate that RPiAE outperforms other visual tokenizers on text-to-image generation and image editing, while delivering the best reconstruction fidelity among representation-based tokenizers.
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。
