通过表示条件扩散模型实现可控图像生成
Towards Controllable Image Generation through Representation-Conditioned Diffusion Models
AI总结：
本文提出利用预训练自监督模型的表示作为条件，通过扩散模型实现无需大量标注的可控图像生成，并探索了表示空间中的平滑和分离特性。
摘要：
扩散模型已成为高质量图像生成和编辑的强大工具，但引导这些模型产生特定输出仍然是一个挑战。传统方法依赖于条件机制，如文本提示或语义图，这些需要大量标注的数据集。在这项初步工作中，我们探索了以预训练自监督模型的表示为条件的扩散模型。自条件机制不仅提高了无条件图像生成的质量，还提供了一个可用于控制生成的表示空间。我们通过识别变化方向来探索这个条件空间，并展示了在平滑性和分离性方面的有前景的特性。
英文摘要：
Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text prompts or semantic maps, which require extensively annotated datasets. In this preliminary work, we explore diffusion models conditioned on representations from a pre-trained self-supervised model. The self-conditioning mechanism not only improves the quality of unconditional image generation, but also provides a representation space that can be used to control the generation. We explore this conditioning space by identifying directions of variations, and demonstrate promising properties in terms of smoothness and disentanglement.
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。
