paper-with-me

Papers

Dimensionality-Varying Diffusion Process

2022-11-29 · CVPR 2023 1 · Han Zhang, Ruili Feng, Zhantao Yang, Lianghua Huang, Yu Liu, Yifei Zhang, Yujun Shen, Deli Zhao, Jingren Zhou, Fan Cheng

Diffusion models, which learn to reverse a signal destruction process to generate new data, typically require the signal at each step to have the same dimension. We argue that, considering the spatial redundancy in image signals, there is no need to maintain a high dimensionality in the evolution process, especially in the early generation phase. To this end, we make a theoretical generalization of the forward diffusion process via signal decomposition. Concretely, we manage to decompose an image into multiple orthogonal components and control the attenuation of each component when perturbing the image. That way, along with the noise strength increasing, we are able to diminish those inconsequential components and thus use a lower-dimensional signal to represent the source, barely losing information. Such a reformulation allows to vary dimensions in both training and inference of diffusion models. Extensive experiments on a range of datasets suggest that our approach substantially reduces the computational cost and achieves on-par or even better synthesis performance compared to baseline methods. We also show that our strategy facilitates high-resolution image synthesis and improves FID of diffusion model trained on FFHQ at $1024\times1024$ resolution from 52.40 to 10.46. Code and models will be made publicly available.

📄 PDF Abstract BibTeX arXiv:2211.16032

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Trans-Dimensional Generative Modeling via Jump Diffusion Models

2023-05-25 · NeurIPS 2023 11 · Andrew Campbell, William Harvey, Christian Weilbach, Valentin De Bortoli 외

We propose a new class of generative models that naturally handle data of varying dimensionality by jointly modeling the state and dimension of each datapoint. The generative process is formulated as a jump diffusion pro…

Imputation

Error Bounds and Optimal Schedules for Masked Diffusions with Factorized Approximations

2025-10-29 · Hugo Lavenant, Giacomo Zanella arxiv

Recently proposed generative models for discrete data, such as Masked Diffusion Models (MDMs), exploit conditional independence approximations to reduce the computational cost of popular Auto-Regressive Models (ARMs), at…

Deep Diffusion Maps

2025-05-09 · Sergio García-Heredia, Ángela Fernández, Carlos M. Alaíz

One of the fundamental problems within the field of machine learning is dimensionality reduction. Dimensionality reduction methods make it possible to combat the so-called curse of dimensionality, visualize high-dimensio…

Dimensionality Reduction

Non-linear dimensionality reduction: Riemannian metric estimation and the problem of geometric discovery

2013-05-30 · Dominique Perraul-Joncas, Marina Meila

In recent years, manifold learning has become increasingly popular as a tool for performing non-linear dimensionality reduction. This has led to the development of numerous algorithms of varying degrees of complexity tha…

Dimensionality Reduction

Nonlinear Dimensionality Reduction with Diffusion Maps in Practice

2026-01-28 · Sönke Beier, Paula Pirker-Díaz, Friedrich Pagenkopf, Karoline Wiesner arxiv

Diffusion Map is a spectral dimensionality reduction technique which is able to uncover nonlinear submanifolds in high-dimensional data. And, it is increasingly applied across a wide range of scientific disciplines, such…

Dimensionality Reduction