GUD: Generation with Unified Diffusion

• URL: http://arxiv.org/abs/2410.02667v1
• Date: Thu, 3 Oct 2024 16:51:14 GMT
• Title: GUD: Generation with Unified Diffusion
• Authors: Mathis Gerdes, Max Welling, Miranda C. N. Cheng,
• Abstract summary: Diffusion generative models transform noise into data by inverting a process that progressively adds noise to data samples. We develop a unified framework for diffusion generative models with greatly enhanced design freedom.
• Score: 40.64742332352373
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion generative models transform noise into data by inverting a process that progressively adds noise to data samples. Inspired by concepts from the renormalization group in physics, which analyzes systems across different scales, we revisit diffusion models by exploring three key design aspects: 1) the choice of representation in which the diffusion process operates (e.g. pixel-, PCA-, Fourier-, or wavelet-basis), 2) the prior distribution that data is transformed into during diffusion (e.g. Gaussian with covariance $\Sigma$), and 3) the scheduling of noise levels applied separately to different parts of the data, captured by a component-wise noise schedule. Incorporating the flexibility in these choices, we develop a unified framework for diffusion generative models with greatly enhanced design freedom. In particular, we introduce soft-conditioning models that smoothly interpolate between standard diffusion models and autoregressive models (in any basis), conceptually bridging these two approaches. Our framework opens up a wide design space which may lead to more efficient training and data generation, and paves the way to novel architectures integrating different generative approaches and generation tasks.

Related papers

• Edge-preserving noise for diffusion models [4.435514696080208]
  We present a novel edge-preserving diffusion model that is a generalization of denoising diffusion probablistic models (DDPM) In particular, we introduce an edge-aware noise scheduler that varies between edge-preserving and isotropic Gaussian noise. We show that our model's generative process converges faster to results that more closely match the target distribution.
  arXiv  Detail & Related papers  (2024-10-02T13:29:52Z)
• Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Density [70.14884528360199]
  We introduce an approach to bias deep generative models, such as GANs and diffusion models, towards generating data with enhanced fidelity or increased diversity. Our approach involves manipulating the distribution of training and generated data through a novel metric for individual samples, named pseudo density.
  arXiv  Detail & Related papers  (2024-07-11T16:46:04Z)
• Denoising Diffusion Bridge Models [54.87947768074036]
  Diffusion models are powerful generative models that map noise to data using processes. For many applications such as image editing, the model input comes from a distribution that is not random noise. In our work, we propose Denoising Diffusion Bridge Models (DDBMs)
  arXiv  Detail & Related papers  (2023-09-29T03:24:24Z)
• DiffFlow: A Unified SDE Framework for Score-Based Diffusion Models and Generative Adversarial Networks [41.451880167535776]
  We propose a unified theoretic framework for explicit generative models (SDMs) and generative adversarial nets (GANs) Under our unified theoretic framework, we introduce several instantiations of the DiffFLow that provide new algorithms beyond GANs and SDMs with exact likelihood inference.
  arXiv  Detail & Related papers  (2023-07-05T10:00:53Z)
• VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation [88.49030739715701]
  This work presents a decomposed diffusion process via resolving the per-frame noise into a base noise that is shared among all frames and a residual noise that varies along the time axis. Experiments on various datasets confirm that our approach, termed as VideoFusion, surpasses both GAN-based and diffusion-based alternatives in high-quality video generation.
  arXiv  Detail & Related papers  (2023-03-15T02:16:39Z)
• Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models [58.357180353368896]
  We propose a conditional paradigm that benefits from the denoising diffusion probabilistic model (DDPM) to tackle the problem of realistic and diverse action-conditioned 3D skeleton-based motion generation. We are a pioneering attempt that uses DDPM to synthesize a variable number of motion sequences conditioned on a categorical action.
  arXiv  Detail & Related papers  (2023-01-10T13:15:42Z)
• Diffusion Models in Vision: A Survey [80.82832715884597]
  A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage. Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens.
  arXiv  Detail & Related papers  (2022-09-10T22:00:30Z)
• Understanding Diffusion Models: A Unified Perspective [0.0]
  Diffusion models have shown incredible capabilities as generative models. We review, demystify, and unify the understanding of diffusion models across both variational and score-based perspectives.
  arXiv  Detail & Related papers  (2022-08-25T09:55:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.