Mirror Diffusion Models
Diffusion models have successfully been applied to generative tasks in various continuous domains. However, applying diffusion to discrete categorical data remains a non-trivial task. Moreover, generation in continuous domains often requires clipping in practice, which motivates the need for a theoretical framework for adapting diffusion to constrained domains. Inspired by the mirror Langevin algorithm for the constrained sampling problem, in this theoretical report we propose Mirror Diffusion Models (MDMs). We demonstrate MDMs in the context of simplex diffusion and propose natural extensions to popular domains such as image and text generation.
Code (0)
등록된 구현이 없습니다.
Tasks
Text GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Neural Approximate Mirror Maps for Constrained Diffusion Models
Diffusion models excel at creating visually-convincing images, but they often struggle to meet subtle constraints inherent in the training data. Such constraints could be physics-based (e.g., satisfying a PDE), geometric…
Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections
We tackle the problem of generating highly realistic and plausible mirror reflections using diffusion-based generative models. We formulate this problem as an image inpainting task, allowing for more user control over th…
Image InpaintingMirrorDiffusion: Stabilizing Diffusion Process in Zero-shot Image Translation by Prompts Redescription and Beyond
Recently, text-to-image diffusion models become a new paradigm in image processing fields, including content generation, image restoration and image-to-image translation. Given a target prompt, Denoising Diffusion Probab…
DenoisingDomain AdaptationImage RestorationImage-to-Image Translation+1Mirror Diffusion Models for Constrained and Watermarked Generation
Modern successes of diffusion models in learning complex, high-dimensional data distributions are attributed, in part, to their capability to construct diffusion processes with analytic transition kernels and score funct…
MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World
Diffusion models have become central to various image editing tasks, yet they often fail to fully adhere to physical laws, particularly with effects like shadows, reflections, and occlusions. In this work, we address the…
Dataset Generation