paper-with-me

Papers

Manifold Preserving Guided Diffusion

2023-11-28 · Yutong He, Naoki Murata, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Dongjun Kim, Wei-Hsiang Liao, Yuki Mitsufuji, J. Zico Kolter, Ruslan Salakhutdinov, Stefano Ermon

Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. In this paper, we propose Manifold Preserving Guided Diffusion (MPGD), a training-free conditional generation framework that leverages pretrained diffusion models and off-the-shelf neural networks with minimal additional inference cost for a broad range of tasks. Specifically, we leverage the manifold hypothesis to refine the guided diffusion steps and introduce a shortcut algorithm in the process. We then propose two methods for on-manifold training-free guidance using pre-trained autoencoders and demonstrate that our shortcut inherently preserves the manifolds when applied to latent diffusion models. Our experiments show that MPGD is efficient and effective for solving a variety of conditional generation applications in low-compute settings, and can consistently offer up to 3.8x speed-ups with the same number of diffusion steps while maintaining high sample quality compared to the baselines.

📄 PDF Abstract BibTeX arXiv:2311.16424

Code (0)

등록된 구현이 없습니다.

Tasks

Conditional Image GenerationImage 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

ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation

2026-02-26 · Ayush Roy, Wei-Yang Alex Lee, Rudrasis Chakraborty, Vishnu Suresh Lokhande arxiv

In recent times, large datasets hinder efficient model training while also containing redundant concepts. Dataset distillation aims to synthesize compact datasets that preserve the knowledge of large-scale training sets …

A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction

2023-05-30 · NeurIPS 2023 11 · Guillaume Huguet, Alexander Tong, Edward De Brouwer, Yanlei Zhang 외

Diffusion-based manifold learning methods have proven useful in representation learning and dimensionality reduction of modern high dimensional, high throughput, noisy datasets. Such datasets are especially present in fi…

DenoisingDimensionality ReductionRepresentation Learning

Supervised Manifold Learning via Random Forest Geometry-Preserving Proximities

2023-07-03 · Jake S. Rhodes

Manifold learning approaches seek the intrinsic, low-dimensional data structure within a high-dimensional space. Mainstream manifold learning algorithms, such as Isomap, UMAP, $t$-SNE, Diffusion Map, and Laplacian Eigenm…

Dimensionality ReductionSupervised dimensionality reduction

Multi-Step Guided Diffusion for Image Restoration on Edge Devices: Toward Lightweight Perception in Embodied AI

2025-06-08 · Aditya Chakravarty

Diffusion models have shown remarkable flexibility for solving inverse problems without task-specific retraining. However, existing approaches such as Manifold Preserving Guided Diffusion (MPGD) apply only a single gradi…

DeblurringDenoisingImage RestorationSuper-Resolution

Diffusion Processes on Implicit Manifolds

2026-04-08 · Victor Kawasaki-Borruat, Clara Grotehans, Pierre Vandergheynst, Adam Gosztolai arxiv

High-dimensional data are often assumed to lie on lower-dimensional manifolds. We study how to construct diffusion processes on this data manifold using only point cloud samples and without access to charts, projections,…