paper-with-me

Papers

Conditional sampling within generative diffusion models

2024-09-15 · Zheng Zhao, Ziwei Luo, Jens Sjölund, Thomas B. Schön

Generative diffusions are a powerful class of Monte Carlo samplers that leverage bridging Markov processes to approximate complex, high-dimensional distributions, such as those found in image processing and language models. Despite their success in these domains, an important open challenge remains: extending these techniques to sample from conditional distributions, as required in, for example, Bayesian inverse problems. In this paper, we present a comprehensive review of existing computational approaches to conditional sampling within generative diffusion models. Specifically, we highlight key methodologies that either utilise the joint distribution, or rely on (pre-trained) marginal distributions with explicit likelihoods, to construct conditional generative samplers.

📄 PDF Abstract BibTeX arXiv:2409.09650

Code (1)

spdes/gdcs 공식 구현 jax

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

Multi-scale Conditional Generative Modeling for Microscopic Image Restoration

2024-07-07 · Luzhe Huang, Xiongye Xiao, Shixuan Li, Jiawen Sun 외

The advance of diffusion-based generative models in recent years has revolutionized state-of-the-art (SOTA) techniques in a wide variety of image analysis and synthesis tasks, whereas their adaptation on image restoratio…

DiversityImage GenerationImage Restoration

Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction

2021-12-09 · CVPR 2022 1 · Hyungjin Chung, Byeongsu Sim, Jong Chul Ye

Diffusion models have recently attained significant interest within the community owing to their strong performance as generative models. Furthermore, its application to inverse problems have demonstrated state-of-the-ar…

compressed sensingImage InpaintingSuper-Resolution

NoiseCtrl: A Sampling-Algorithm-Agnostic Conditional Generation Method for Diffusion Models

2025-01-01 · CVPR 2025 1 · Longquan Dai, He Wang, Jinhui Tang

In training-free conditional generative tasks, diffusion models utilize differentiable loss functions to steer the generative reverse process, necessitating modifications to sampling algorithms like DDPM and DDIM. Ho…

Conditional Image GenerationImage Generation

Generative Modeling of Seismic Data using Diffusion Models and its Application to Multi-Purpose Seismic Inverse Problems

2025-03-06 · 86th EAGE Annual Conference & Exhibition 2025 3 · Chuangji Meng, Jinghuai Gao, Yajun Tian, Hongling Chen 외

Efficient solutions to inverse problems often require supervised training with labeled data to model posterior distributions, such as using conditional diffusion models in seismic applications. However, these methods are…

compressed sensingDenoising

Improving Diffusion-Based Generative Models via Approximated Optimal Transport

2024-03-08 · Daegyu Kim, Jooyoung Choi, Chaehun Shin, Uiwon Hwang 외

We introduce the Approximated Optimal Transport (AOT) technique, a novel training scheme for diffusion-based generative models. Our approach aims to approximate and integrate optimal transport into the training process, …

Image Generation